filesystem notification: create fs/notify to contain all fs notification

Creating a generic filesystem notification interface, fsnotify, which will be
used by inotify, dnotify, and eventually fanotify is really starting to
clutter the fs directory.  This patch simply moves inotify and dnotify into
fs/notify/inotify and fs/notify/dnotify respectively to make both current fs/
and future notification tidier.

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

9 files changed, 1926 insertions, 0 deletions

diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
new file mode 100644
index 000000000000..50914d7303c6
--- /dev/null
+++ b/fs/notify/Kconfig
@@ -0,0 +1,2 @@
+source "fs/notify/dnotify/Kconfig"
+source "fs/notify/inotify/Kconfig"
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
new file mode 100644
index 000000000000..5a95b6010ce7
--- /dev/null
+++ b/fs/notify/Makefile
@@ -0,0 +1,2 @@
+obj-y			+= dnotify/
+obj-y			+= inotify/
diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig
new file mode 100644
index 000000000000..26adf5dfa646
--- /dev/null
+++ b/fs/notify/dnotify/Kconfig
@@ -0,0 +1,10 @@
+config DNOTIFY
+	bool "Dnotify support"
+	default y
+	help
+	  Dnotify is a directory-based per-fd file change notification system
+	  that uses signals to communicate events to user-space.  There exist
+	  superior alternatives, but some applications may still rely on
+	  dnotify.
+
+	  If unsure, say Y.
diff --git a/fs/notify/dnotify/Makefile b/fs/notify/dnotify/Makefile
new file mode 100644
index 000000000000..f145251dcadb
--- /dev/null
+++ b/fs/notify/dnotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_DNOTIFY)		+= dnotify.o
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
new file mode 100644
index 000000000000..b0aa2cde80bd
--- /dev/null
+++ b/fs/notify/dnotify/dnotify.c
@@ -0,0 +1,191 @@
+/*
+ * Directory notifications for Linux.
+ *
+ * Copyright (C) 2000,2001,2002 Stephen Rothwell
+ *
+ * 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/fs.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/dnotify.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/fdtable.h>
+
+int dir_notify_enable __read_mostly = 1;
+
+static struct kmem_cache *dn_cache __read_mostly;
+
+static void redo_inode_mask(struct inode *inode)
+{
+	unsigned long new_mask;
+	struct dnotify_struct *dn;
+
+	new_mask = 0;
+	for (dn = inode->i_dnotify; dn != NULL; dn = dn->dn_next)
+		new_mask |= dn->dn_mask & ~DN_MULTISHOT;
+	inode->i_dnotify_mask = new_mask;
+}
+
+void dnotify_flush(struct file *filp, fl_owner_t id)
+{
+	struct dnotify_struct *dn;
+	struct dnotify_struct **prev;
+	struct inode *inode;
+
+	inode = filp->f_path.dentry->d_inode;
+	if (!S_ISDIR(inode->i_mode))
+		return;
+	spin_lock(&inode->i_lock);
+	prev = &inode->i_dnotify;
+	while ((dn = *prev) != NULL) {
+		if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
+			*prev = dn->dn_next;
+			redo_inode_mask(inode);
+			kmem_cache_free(dn_cache, dn);
+			break;
+		}
+		prev = &dn->dn_next;
+	}
+	spin_unlock(&inode->i_lock);
+}
+
+int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
+{
+	struct dnotify_struct *dn;
+	struct dnotify_struct *odn;
+	struct dnotify_struct **prev;
+	struct inode *inode;
+	fl_owner_t id = current->files;
+	struct file *f;
+	int error = 0;
+
+	if ((arg & ~DN_MULTISHOT) == 0) {
+		dnotify_flush(filp, id);
+		return 0;
+	}
+	if (!dir_notify_enable)
+		return -EINVAL;
+	inode = filp->f_path.dentry->d_inode;
+	if (!S_ISDIR(inode->i_mode))
+		return -ENOTDIR;
+	dn = kmem_cache_alloc(dn_cache, GFP_KERNEL);
+	if (dn == NULL)
+		return -ENOMEM;
+	spin_lock(&inode->i_lock);
+	prev = &inode->i_dnotify;
+	while ((odn = *prev) != NULL) {
+		if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
+			odn->dn_fd = fd;
+			odn->dn_mask |= arg;
+			inode->i_dnotify_mask |= arg & ~DN_MULTISHOT;
+			goto out_free;
+		}
+		prev = &odn->dn_next;
+	}
+
+	rcu_read_lock();
+	f = fcheck(fd);
+	rcu_read_unlock();
+	/* we'd lost the race with close(), sod off silently */
+	/* note that inode->i_lock prevents reordering problems
+	 * between accesses to descriptor table and ->i_dnotify */
+	if (f != filp)
+		goto out_free;
+
+	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
+	if (error)
+		goto out_free;
+
+	dn->dn_mask = arg;
+	dn->dn_fd = fd;
+	dn->dn_filp = filp;
+	dn->dn_owner = id;
+	inode->i_dnotify_mask |= arg & ~DN_MULTISHOT;
+	dn->dn_next = inode->i_dnotify;
+	inode->i_dnotify = dn;
+	spin_unlock(&inode->i_lock);
+	return 0;
+
+out_free:
+	spin_unlock(&inode->i_lock);
+	kmem_cache_free(dn_cache, dn);
+	return error;
+}
+
+void __inode_dir_notify(struct inode *inode, unsigned long event)
+{
+	struct dnotify_struct *	dn;
+	struct dnotify_struct **prev;
+	struct fown_struct *	fown;
+	int			changed = 0;
+
+	spin_lock(&inode->i_lock);
+	prev = &inode->i_dnotify;
+	while ((dn = *prev) != NULL) {
+		if ((dn->dn_mask & event) == 0) {
+			prev = &dn->dn_next;
+			continue;
+		}
+		fown = &dn->dn_filp->f_owner;
+		send_sigio(fown, dn->dn_fd, POLL_MSG);
+		if (dn->dn_mask & DN_MULTISHOT)
+			prev = &dn->dn_next;
+		else {
+			*prev = dn->dn_next;
+			changed = 1;
+			kmem_cache_free(dn_cache, dn);
+		}
+	}
+	if (changed)
+		redo_inode_mask(inode);
+	spin_unlock(&inode->i_lock);
+}
+
+EXPORT_SYMBOL(__inode_dir_notify);
+
+/*
+ * This is hopelessly wrong, but unfixable without API changes.  At
+ * least it doesn't oops the kernel...
+ *
+ * To safely access ->d_parent we need to keep d_move away from it.  Use the
+ * dentry's d_lock for this.
+ */
+void dnotify_parent(struct dentry *dentry, unsigned long event)
+{
+	struct dentry *parent;
+
+	if (!dir_notify_enable)
+		return;
+
+	spin_lock(&dentry->d_lock);
+	parent = dentry->d_parent;
+	if (parent->d_inode->i_dnotify_mask & event) {
+		dget(parent);
+		spin_unlock(&dentry->d_lock);
+		__inode_dir_notify(parent->d_inode, event);
+		dput(parent);
+	} else {
+		spin_unlock(&dentry->d_lock);
+	}
+}
+EXPORT_SYMBOL_GPL(dnotify_parent);
+
+static int __init dnotify_init(void)
+{
+	dn_cache = kmem_cache_create("dnotify_cache",
+		sizeof(struct dnotify_struct), 0, SLAB_PANIC, NULL);
+	return 0;
+}
+
+module_init(dnotify_init)
diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
new file mode 100644
index 000000000000..446792841023
--- /dev/null
+++ b/fs/notify/inotify/Kconfig
@@ -0,0 +1,27 @@
+config INOTIFY
+	bool "Inotify file change notification support"
+	default y
+	---help---
+	  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 <file: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 <file:Documentation/filesystems/inotify.txt>
+
+	  If unsure, say Y.
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
new file mode 100644
index 000000000000..e290f3bb9d8d
--- /dev/null
+++ b/fs/notify/inotify/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_INOTIFY)		+= inotify.o
+obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
diff --git a/fs/notify/inotify/inotify.c b/fs/notify/inotify/inotify.c
new file mode 100644
index 000000000000..dae3f28f30d4
--- /dev/null
+++ b/fs/notify/inotify/inotify.c
@@ -0,0 +1,913 @@
+/*
+ * fs/inotify.c - inode-based file event notifications
+ *
+ * Authors:
+ *	John McCutchan	<ttb@tentacle.dhs.org>
+ *	Robert Love	<rml@novell.com>
+ *
+ * Kernel API added by: Amy Griffis <amy.griffis@hp.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/module.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/writeback.h>
+#include <linux/inotify.h>
+
+static atomic_t inotify_cookie;
+
+/*
+ * 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_handle->mutex (protects inotify_handle and watches->h_list)
+ *
+ * The inode->inotify_mutex and inotify_handle->mutex and held during execution
+ * of a caller's event handler.  Thus, the caller must not hold any locks
+ * taken in their event handler while calling any of the published inotify
+ * interfaces.
+ */
+
+/*
+ * Lifetimes of the three main data structures--inotify_handle, inode, and
+ * inotify_watch--are managed by reference count.
+ *
+ * inotify_handle: Lifetime is from inotify_init() to inotify_destroy().
+ * Additional references can bump the count via get_inotify_handle() and drop
+ * the count via put_inotify_handle().
+ *
+ * inotify_watch: for inotify's purposes, lifetime is from inotify_add_watch()
+ * to remove_watch_no_event().  Additional references can bump the count via
+ * get_inotify_watch() and drop the count via put_inotify_watch().  The caller
+ * is reponsible for the final put after receiving IN_IGNORED, or when using
+ * IN_ONESHOT after receiving the first event.  Inotify does the final put if
+ * inotify_destroy() is called.
+ *
+ * inode: Pinned so long as the inode is associated with a watch, from
+ * inotify_add_watch() to the final put_inotify_watch().
+ */
+
+/*
+ * struct inotify_handle - represents an inotify instance
+ *
+ * This structure is protected by the mutex 'mutex'.
+ */
+struct inotify_handle {
+	struct idr		idr;		/* idr mapping wd -> watch */
+	struct mutex		mutex;		/* protects this bad boy */
+	struct list_head	watches;	/* list of watches */
+	atomic_t		count;		/* reference count */
+	u32			last_wd;	/* the last wd allocated */
+	const struct inotify_operations *in_ops; /* inotify caller operations */
+};
+
+static inline void get_inotify_handle(struct inotify_handle *ih)
+{
+	atomic_inc(&ih->count);
+}
+
+static inline void put_inotify_handle(struct inotify_handle *ih)
+{
+	if (atomic_dec_and_test(&ih->count)) {
+		idr_destroy(&ih->idr);
+		kfree(ih);
+	}
+}
+
+/**
+ * get_inotify_watch - grab a reference to an inotify_watch
+ * @watch: watch to grab
+ */
+void get_inotify_watch(struct inotify_watch *watch)
+{
+	atomic_inc(&watch->count);
+}
+EXPORT_SYMBOL_GPL(get_inotify_watch);
+
+int pin_inotify_watch(struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	spin_lock(&sb_lock);
+	if (sb->s_count >= S_BIAS) {
+		atomic_inc(&sb->s_active);
+		spin_unlock(&sb_lock);
+		atomic_inc(&watch->count);
+		return 1;
+	}
+	spin_unlock(&sb_lock);
+	return 0;
+}
+
+/**
+ * put_inotify_watch - decrements the ref count on a given watch.  cleans up
+ * watch references if the count reaches zero.  inotify_watch is freed by
+ * inotify callers via the destroy_watch() op.
+ * @watch: watch to release
+ */
+void put_inotify_watch(struct inotify_watch *watch)
+{
+	if (atomic_dec_and_test(&watch->count)) {
+		struct inotify_handle *ih = watch->ih;
+
+		iput(watch->inode);
+		ih->in_ops->destroy_watch(watch);
+		put_inotify_handle(ih);
+	}
+}
+EXPORT_SYMBOL_GPL(put_inotify_watch);
+
+void unpin_inotify_watch(struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	put_inotify_watch(watch);
+	deactivate_super(sb);
+}
+
+/*
+ * inotify_handle_get_wd - returns the next WD for use by the given handle
+ *
+ * Callers must hold ih->mutex.  This function can sleep.
+ */
+static int inotify_handle_get_wd(struct inotify_handle *ih,
+				 struct inotify_watch *watch)
+{
+	int ret;
+
+	do {
+		if (unlikely(!idr_pre_get(&ih->idr, GFP_KERNEL)))
+			return -ENOSPC;
+		ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
+	} while (ret == -EAGAIN);
+
+	if (likely(!ret))
+		ih->last_wd = watch->wd;
+
+	return ret;
+}
+
+/*
+ * inotify_inode_watched - returns nonzero if there are watches on this inode
+ * and zero otherwise.  We call this lockless, we do not care if we race.
+ */
+static inline int inotify_inode_watched(struct inode *inode)
+{
+	return !list_empty(&inode->inotify_watches);
+}
+
+/*
+ * Get child dentry flag into synch with parent inode.
+ * Flag should always be clear for negative dentrys.
+ */
+static void set_dentry_child_flags(struct inode *inode, int watched)
+{
+	struct dentry *alias;
+
+	spin_lock(&dcache_lock);
+	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+		struct dentry *child;
+
+		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+			if (!child->d_inode)
+				continue;
+
+			spin_lock(&child->d_lock);
+			if (watched)
+				child->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
+			else
+				child->d_flags &=~DCACHE_INOTIFY_PARENT_WATCHED;
+			spin_unlock(&child->d_lock);
+		}
+	}
+	spin_unlock(&dcache_lock);
+}
+
+/*
+ * inotify_find_handle - find the watch associated with the given inode and
+ * handle
+ *
+ * Callers must hold inode->inotify_mutex.
+ */
+static struct inotify_watch *inode_find_handle(struct inode *inode,
+					       struct inotify_handle *ih)
+{
+	struct inotify_watch *watch;
+
+	list_for_each_entry(watch, &inode->inotify_watches, i_list) {
+		if (watch->ih == ih)
+			return watch;
+	}
+
+	return NULL;
+}
+
+/*
+ * remove_watch_no_event - remove watch without the IN_IGNORED event.
+ *
+ * Callers must hold both inode->inotify_mutex and ih->mutex.
+ */
+static void remove_watch_no_event(struct inotify_watch *watch,
+				  struct inotify_handle *ih)
+{
+	list_del(&watch->i_list);
+	list_del(&watch->h_list);
+
+	if (!inotify_inode_watched(watch->inode))
+		set_dentry_child_flags(watch->inode, 0);
+
+	idr_remove(&ih->idr, watch->wd);
+}
+
+/**
+ * inotify_remove_watch_locked - Remove a watch from both the handle and the
+ * inode.  Sends the IN_IGNORED event signifying that the inode is no longer
+ * watched.  May be invoked from a caller's event handler.
+ * @ih: inotify handle associated with watch
+ * @watch: watch to remove
+ *
+ * Callers must hold both inode->inotify_mutex and ih->mutex.
+ */
+void inotify_remove_watch_locked(struct inotify_handle *ih,
+				 struct inotify_watch *watch)
+{
+	remove_watch_no_event(watch, ih);
+	ih->in_ops->handle_event(watch, watch->wd, IN_IGNORED, 0, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(inotify_remove_watch_locked);
+
+/* Kernel API for producing events */
+
+/*
+ * inotify_d_instantiate - instantiate dcache entry for inode
+ */
+void inotify_d_instantiate(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *parent;
+
+	if (!inode)
+		return;
+
+	spin_lock(&entry->d_lock);
+	parent = entry->d_parent;
+	if (parent->d_inode && inotify_inode_watched(parent->d_inode))
+		entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
+	spin_unlock(&entry->d_lock);
+}
+
+/*
+ * inotify_d_move - dcache entry has been moved
+ */
+void inotify_d_move(struct dentry *entry)
+{
+	struct dentry *parent;
+
+	parent = entry->d_parent;
+	if (inotify_inode_watched(parent->d_inode))
+		entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
+	else
+		entry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED;
+}
+
+/**
+ * inotify_inode_queue_event - queue an event to all watches on this inode
+ * @inode: inode event is originating from
+ * @mask: event mask describing this event
+ * @cookie: cookie for synchronization, or zero
+ * @name: filename, if any
+ * @n_inode: inode associated with name
+ */
+void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
+			       const char *name, struct inode *n_inode)
+{
+	struct inotify_watch *watch, *next;
+
+	if (!inotify_inode_watched(inode))
+		return;
+
+	mutex_lock(&inode->inotify_mutex);
+	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
+		u32 watch_mask = watch->mask;
+		if (watch_mask & mask) {
+			struct inotify_handle *ih= watch->ih;
+			mutex_lock(&ih->mutex);
+			if (watch_mask & IN_ONESHOT)
+				remove_watch_no_event(watch, ih);
+			ih->in_ops->handle_event(watch, watch->wd, mask, cookie,
+						 name, n_inode);
+			mutex_unlock(&ih->mutex);
+		}
+	}
+	mutex_unlock(&inode->inotify_mutex);
+}
+EXPORT_SYMBOL_GPL(inotify_inode_queue_event);
+
+/**
+ * inotify_dentry_parent_queue_event - queue an event to a dentry's parent
+ * @dentry: the dentry in question, we queue against this dentry's parent
+ * @mask: event mask describing this event
+ * @cookie: cookie for synchronization, or zero
+ * @name: filename, if any
+ */
+void inotify_dentry_parent_queue_event(struct dentry *dentry, u32 mask,
+				       u32 cookie, const char *name)
+{
+	struct dentry *parent;
+	struct inode *inode;
+
+	if (!(dentry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED))
+		return;
+
+	spin_lock(&dentry->d_lock);
+	parent = dentry->d_parent;
+	inode = parent->d_inode;
+
+	if (inotify_inode_watched(inode)) {
+		dget(parent);
+		spin_unlock(&dentry->d_lock);
+		inotify_inode_queue_event(inode, mask, cookie, name,
+					  dentry->d_inode);
+		dput(parent);
+	} else
+		spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL_GPL(inotify_dentry_parent_queue_event);
+
+/**
+ * inotify_get_cookie - return a unique cookie for use in synchronizing events.
+ */
+u32 inotify_get_cookie(void)
+{
+	return atomic_inc_return(&inotify_cookie);
+}
+EXPORT_SYMBOL_GPL(inotify_get_cookie);
+
+/**
+ * inotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
+ * @list: list of inodes being unmounted (sb->s_inodes)
+ *
+ * Called with inode_lock held, protecting the unmounting super block's list
+ * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
+ * We temporarily drop inode_lock, however, and CAN block.
+ */
+void inotify_unmount_inodes(struct list_head *list)
+{
+	struct inode *inode, *next_i, *need_iput = NULL;
+
+	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+		struct inotify_watch *watch, *next_w;
+		struct inode *need_iput_tmp;
+		struct list_head *watches;
+
+		/*
+		 * If i_count is zero, the inode cannot have any watches and
+		 * doing an __iget/iput with MS_ACTIVE clear would actually
+		 * evict all inodes with zero i_count from icache which is
+		 * unnecessarily violent and may in fact be illegal to do.
+		 */
+		if (!atomic_read(&inode->i_count))
+			continue;
+
+		/*
+		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING, or
+		 * I_WILL_FREE which is fine because by that point the inode
+		 * cannot have any associated watches.
+		 */
+		if (inode->i_state & (I_CLEAR | I_FREEING | I_WILL_FREE))
+			continue;
+
+		need_iput_tmp = need_iput;
+		need_iput = NULL;
+		/* In case inotify_remove_watch_locked() drops a reference. */
+		if (inode != need_iput_tmp)
+			__iget(inode);
+		else
+			need_iput_tmp = NULL;
+		/* In case the dropping of a reference would nuke next_i. */
+		if ((&next_i->i_sb_list != list) &&
+				atomic_read(&next_i->i_count) &&
+				!(next_i->i_state & (I_CLEAR | I_FREEING |
+					I_WILL_FREE))) {
+			__iget(next_i);
+			need_iput = next_i;
+		}
+
+		/*
+		 * We can safely drop inode_lock here because we hold
+		 * references on both inode and next_i.  Also no new inodes
+		 * will be added since the umount has begun.  Finally,
+		 * iprune_mutex keeps shrink_icache_memory() away.
+		 */
+		spin_unlock(&inode_lock);
+
+		if (need_iput_tmp)
+			iput(need_iput_tmp);
+
+		/* for each watch, send IN_UNMOUNT and then remove it */
+		mutex_lock(&inode->inotify_mutex);
+		watches = &inode->inotify_watches;
+		list_for_each_entry_safe(watch, next_w, watches, i_list) {
+			struct inotify_handle *ih= watch->ih;
+			get_inotify_watch(watch);
+			mutex_lock(&ih->mutex);
+			ih->in_ops->handle_event(watch, watch->wd, IN_UNMOUNT, 0,
+						 NULL, NULL);
+			inotify_remove_watch_locked(ih, watch);
+			mutex_unlock(&ih->mutex);
+			put_inotify_watch(watch);
+		}
+		mutex_unlock(&inode->inotify_mutex);
+		iput(inode);		
+
+		spin_lock(&inode_lock);
+	}
+}
+EXPORT_SYMBOL_GPL(inotify_unmount_inodes);
+
+/**
+ * inotify_inode_is_dead - an inode has been deleted, cleanup any watches
+ * @inode: inode that is about to be removed
+ */
+void inotify_inode_is_dead(struct inode *inode)
+{
+	struct inotify_watch *watch, *next;
+
+	mutex_lock(&inode->inotify_mutex);
+	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
+		struct inotify_handle *ih = watch->ih;
+		mutex_lock(&ih->mutex);
+		inotify_remove_watch_locked(ih, watch);
+		mutex_unlock(&ih->mutex);
+	}
+	mutex_unlock(&inode->inotify_mutex);
+}
+EXPORT_SYMBOL_GPL(inotify_inode_is_dead);
+
+/* Kernel Consumer API */
+
+/**
+ * inotify_init - allocate and initialize an inotify instance
+ * @ops: caller's inotify operations
+ */
+struct inotify_handle *inotify_init(const struct inotify_operations *ops)
+{
+	struct inotify_handle *ih;
+
+	ih = kmalloc(sizeof(struct inotify_handle), GFP_KERNEL);
+	if (unlikely(!ih))
+		return ERR_PTR(-ENOMEM);
+
+	idr_init(&ih->idr);
+	INIT_LIST_HEAD(&ih->watches);
+	mutex_init(&ih->mutex);
+	ih->last_wd = 0;
+	ih->in_ops = ops;
+	atomic_set(&ih->count, 0);
+	get_inotify_handle(ih);
+
+	return ih;
+}
+EXPORT_SYMBOL_GPL(inotify_init);
+
+/**
+ * inotify_init_watch - initialize an inotify watch
+ * @watch: watch to initialize
+ */
+void inotify_init_watch(struct inotify_watch *watch)
+{
+	INIT_LIST_HEAD(&watch->h_list);
+	INIT_LIST_HEAD(&watch->i_list);
+	atomic_set(&watch->count, 0);
+	get_inotify_watch(watch); /* initial get */
+}
+EXPORT_SYMBOL_GPL(inotify_init_watch);
+
+/*
+ * Watch removals suck violently.  To kick the watch out we need (in this
+ * order) inode->inotify_mutex and ih->mutex.  That's fine if we have
+ * a hold on inode; however, for all other cases we need to make damn sure
+ * we don't race with umount.  We can *NOT* just grab a reference to a
+ * watch - inotify_unmount_inodes() will happily sail past it and we'll end
+ * with reference to inode potentially outliving its superblock.  Ideally
+ * we just want to grab an active reference to superblock if we can; that
+ * will make sure we won't go into inotify_umount_inodes() until we are
+ * done.  Cleanup is just deactivate_super().  However, that leaves a messy
+ * case - what if we *are* racing with umount() and active references to
+ * superblock can't be acquired anymore?  We can bump ->s_count, grab
+ * ->s_umount, which will almost certainly wait until the superblock is shut
+ * down and the watch in question is pining for fjords.  That's fine, but
+ * there is a problem - we might have hit the window between ->s_active
+ * getting to 0 / ->s_count - below S_BIAS (i.e. the moment when superblock
+ * is past the point of no return and is heading for shutdown) and the
+ * moment when deactivate_super() acquires ->s_umount.  We could just do
+ * drop_super() yield() and retry, but that's rather antisocial and this
+ * stuff is luser-triggerable.  OTOH, having grabbed ->s_umount and having
+ * found that we'd got there first (i.e. that ->s_root is non-NULL) we know
+ * that we won't race with inotify_umount_inodes().  So we could grab a
+ * reference to watch and do the rest as above, just with drop_super() instead
+ * of deactivate_super(), right?  Wrong.  We had to drop ih->mutex before we
+ * could grab ->s_umount.  So the watch could've been gone already.
+ *
+ * That still can be dealt with - we need to save watch->wd, do idr_find()
+ * and compare its result with our pointer.  If they match, we either have
+ * the damn thing still alive or we'd lost not one but two races at once,
+ * the watch had been killed and a new one got created with the same ->wd
+ * at the same address.  That couldn't have happened in inotify_destroy(),
+ * but inotify_rm_wd() could run into that.  Still, "new one got created"
+ * is not a problem - we have every right to kill it or leave it alone,
+ * whatever's more convenient.
+ *
+ * So we can use idr_find(...) == watch && watch->inode->i_sb == sb as
+ * "grab it and kill it" check.  If it's been our original watch, we are
+ * fine, if it's a newcomer - nevermind, just pretend that we'd won the
+ * race and kill the fscker anyway; we are safe since we know that its
+ * superblock won't be going away.
+ *
+ * And yes, this is far beyond mere "not very pretty"; so's the entire
+ * concept of inotify to start with.
+ */
+
+/**
+ * pin_to_kill - pin the watch down for removal
+ * @ih: inotify handle
+ * @watch: watch to kill
+ *
+ * Called with ih->mutex held, drops it.  Possible return values:
+ * 0 - nothing to do, it has died
+ * 1 - remove it, drop the reference and deactivate_super()
+ * 2 - remove it, drop the reference and drop_super(); we tried hard to avoid
+ * that variant, since it involved a lot of PITA, but that's the best that
+ * could've been done.
+ */
+static int pin_to_kill(struct inotify_handle *ih, struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	s32 wd = watch->wd;
+
+	spin_lock(&sb_lock);
+	if (sb->s_count >= S_BIAS) {
+		atomic_inc(&sb->s_active);
+		spin_unlock(&sb_lock);
+		get_inotify_watch(watch);
+		mutex_unlock(&ih->mutex);
+		return 1;	/* the best outcome */
+	}
+	sb->s_count++;
+	spin_unlock(&sb_lock);
+	mutex_unlock(&ih->mutex); /* can't grab ->s_umount under it */
+	down_read(&sb->s_umount);
+	if (likely(!sb->s_root)) {
+		/* fs is already shut down; the watch is dead */
+		drop_super(sb);
+		return 0;
+	}
+	/* raced with the final deactivate_super() */
+	mutex_lock(&ih->mutex);
+	if (idr_find(&ih->idr, wd) != watch || watch->inode->i_sb != sb) {
+		/* the watch is dead */
+		mutex_unlock(&ih->mutex);
+		drop_super(sb);
+		return 0;
+	}
+	/* still alive or freed and reused with the same sb and wd; kill */
+	get_inotify_watch(watch);
+	mutex_unlock(&ih->mutex);
+	return 2;
+}
+
+static void unpin_and_kill(struct inotify_watch *watch, int how)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	put_inotify_watch(watch);
+	switch (how) {
+	case 1:
+		deactivate_super(sb);
+		break;
+	case 2:
+		drop_super(sb);
+	}
+}
+
+/**
+ * inotify_destroy - clean up and destroy an inotify instance
+ * @ih: inotify handle
+ */
+void inotify_destroy(struct inotify_handle *ih)
+{
+	/*
+	 * Destroy all of the watches for this handle. Unfortunately, not very
+	 * pretty.  We cannot do a simple iteration over the list, because we
+	 * do not know the inode until we iterate to the watch.  But we need to
+	 * hold inode->inotify_mutex before ih->mutex.  The following works.
+	 *
+	 * AV: it had to become even uglier to start working ;-/
+	 */
+	while (1) {
+		struct inotify_watch *watch;
+		struct list_head *watches;
+		struct super_block *sb;
+		struct inode *inode;
+		int how;
+
+		mutex_lock(&ih->mutex);
+		watches = &ih->watches;
+		if (list_empty(watches)) {
+			mutex_unlock(&ih->mutex);
+			break;
+		}
+		watch = list_first_entry(watches, struct inotify_watch, h_list);
+		sb = watch->inode->i_sb;
+		how = pin_to_kill(ih, watch);
+		if (!how)
+			continue;
+
+		inode = watch->inode;
+		mutex_lock(&inode->inotify_mutex);
+		mutex_lock(&ih->mutex);
+
+		/* make sure we didn't race with another list removal */
+		if (likely(idr_find(&ih->idr, watch->wd))) {
+			remove_watch_no_event(watch, ih);
+			put_inotify_watch(watch);
+		}
+
+		mutex_unlock(&ih->mutex);
+		mutex_unlock(&inode->inotify_mutex);
+		unpin_and_kill(watch, how);
+	}
+
+	/* free this handle: the put matching the get in inotify_init() */
+	put_inotify_handle(ih);
+}
+EXPORT_SYMBOL_GPL(inotify_destroy);
+
+/**
+ * inotify_find_watch - find an existing watch for an (ih,inode) pair
+ * @ih: inotify handle
+ * @inode: inode to watch
+ * @watchp: pointer to existing inotify_watch
+ *
+ * Caller must pin given inode (via nameidata).
+ */
+s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
+		       struct inotify_watch **watchp)
+{
+	struct inotify_watch *old;
+	int ret = -ENOENT;
+
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
+
+	old = inode_find_handle(inode, ih);
+	if (unlikely(old)) {
+		get_inotify_watch(old); /* caller must put watch */
+		*watchp = old;
+		ret = old->wd;
+	}
+
+	mutex_unlock(&ih->mutex);
+	mutex_unlock(&inode->inotify_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(inotify_find_watch);
+
+/**
+ * inotify_find_update_watch - find and update the mask of an existing watch
+ * @ih: inotify handle
+ * @inode: inode's watch to update
+ * @mask: mask of events to watch
+ *
+ * Caller must pin given inode (via nameidata).
+ */
+s32 inotify_find_update_watch(struct inotify_handle *ih, struct inode *inode,
+			      u32 mask)
+{
+	struct inotify_watch *old;
+	int mask_add = 0;
+	int ret;
+
+	if (mask & IN_MASK_ADD)
+		mask_add = 1;
+
+	/* don't allow invalid bits: we don't want flags set */
+	mask &= IN_ALL_EVENTS | IN_ONESHOT;
+	if (unlikely(!mask))
+		return -EINVAL;
+
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
+
+	/*
+	 * Handle the case of re-adding a watch on an (inode,ih) pair that we
+	 * are already watching.  We just update the mask and return its wd.
+	 */
+	old = inode_find_handle(inode, ih);
+	if (unlikely(!old)) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	if (mask_add)
+		old->mask |= mask;
+	else
+		old->mask = mask;
+	ret = old->wd;
+out:
+	mutex_unlock(&ih->mutex);
+	mutex_unlock(&inode->inotify_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(inotify_find_update_watch);
+
+/**
+ * inotify_add_watch - add a watch to an inotify instance
+ * @ih: inotify handle
+ * @watch: caller allocated watch structure
+ * @inode: inode to watch
+ * @mask: mask of events to watch
+ *
+ * Caller must pin given inode (via nameidata).
+ * Caller must ensure it only calls inotify_add_watch() once per watch.
+ * Calls inotify_handle_get_wd() so may sleep.
+ */
+s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch,
+		      struct inode *inode, u32 mask)
+{
+	int ret = 0;
+	int newly_watched;
+
+	/* don't allow invalid bits: we don't want flags set */
+	mask &= IN_ALL_EVENTS | IN_ONESHOT;
+	if (unlikely(!mask))
+		return -EINVAL;
+	watch->mask = mask;
+
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
+
+	/* Initialize a new watch */
+	ret = inotify_handle_get_wd(ih, watch);
+	if (unlikely(ret))
+		goto out;
+	ret = watch->wd;
+
+	/* save a reference to handle and bump the count to make it official */
+	get_inotify_handle(ih);
+	watch->ih = ih;
+
+	/*
+	 * Save a reference to the inode and bump the ref count to make it
+	 * official.  We hold a reference to nameidata, which makes this safe.
+	 */
+	watch->inode = igrab(inode);
+
+	/* Add the watch to the handle's and the inode's list */
+	newly_watched = !inotify_inode_watched(inode);
+	list_add(&watch->h_list, &ih->watches);
+	list_add(&watch->i_list, &inode->inotify_watches);
+	/*
+	 * Set child flags _after_ adding the watch, so there is no race
+	 * windows where newly instantiated children could miss their parent's
+	 * watched flag.
+	 */
+	if (newly_watched)
+		set_dentry_child_flags(inode, 1);
+
+out:
+	mutex_unlock(&ih->mutex);
+	mutex_unlock(&inode->inotify_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(inotify_add_watch);
+
+/**
+ * inotify_clone_watch - put the watch next to existing one
+ * @old: already installed watch
+ * @new: new watch
+ *
+ * Caller must hold the inotify_mutex of inode we are dealing with;
+ * it is expected to remove the old watch before unlocking the inode.
+ */
+s32 inotify_clone_watch(struct inotify_watch *old, struct inotify_watch *new)
+{
+	struct inotify_handle *ih = old->ih;
+	int ret = 0;
+
+	new->mask = old->mask;
+	new->ih = ih;
+
+	mutex_lock(&ih->mutex);
+
+	/* Initialize a new watch */
+	ret = inotify_handle_get_wd(ih, new);
+	if (unlikely(ret))
+		goto out;
+	ret = new->wd;
+
+	get_inotify_handle(ih);
+
+	new->inode = igrab(old->inode);
+
+	list_add(&new->h_list, &ih->watches);
+	list_add(&new->i_list, &old->inode->inotify_watches);
+out:
+	mutex_unlock(&ih->mutex);
+	return ret;
+}
+
+void inotify_evict_watch(struct inotify_watch *watch)
+{
+	get_inotify_watch(watch);
+	mutex_lock(&watch->ih->mutex);
+	inotify_remove_watch_locked(watch->ih, watch);
+	mutex_unlock(&watch->ih->mutex);
+}
+
+/**
+ * inotify_rm_wd - remove a watch from an inotify instance
+ * @ih: inotify handle
+ * @wd: watch descriptor to remove
+ *
+ * Can sleep.
+ */
+int inotify_rm_wd(struct inotify_handle *ih, u32 wd)
+{
+	struct inotify_watch *watch;
+	struct super_block *sb;
+	struct inode *inode;
+	int how;
+
+	mutex_lock(&ih->mutex);
+	watch = idr_find(&ih->idr, wd);
+	if (unlikely(!watch)) {
+		mutex_unlock(&ih->mutex);
+		return -EINVAL;
+	}
+	sb = watch->inode->i_sb;
+	how = pin_to_kill(ih, watch);
+	if (!how)
+		return 0;
+
+	inode = watch->inode;
+
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
+
+	/* make sure that we did not race */
+	if (likely(idr_find(&ih->idr, wd) == watch))
+		inotify_remove_watch_locked(ih, watch);
+
+	mutex_unlock(&ih->mutex);
+	mutex_unlock(&inode->inotify_mutex);
+	unpin_and_kill(watch, how);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(inotify_rm_wd);
+
+/**
+ * inotify_rm_watch - remove a watch from an inotify instance
+ * @ih: inotify handle
+ * @watch: watch to remove
+ *
+ * Can sleep.
+ */
+int inotify_rm_watch(struct inotify_handle *ih,
+		     struct inotify_watch *watch)
+{
+	return inotify_rm_wd(ih, watch->wd);
+}
+EXPORT_SYMBOL_GPL(inotify_rm_watch);
+
+/*
+ * inotify_setup - core initialization function
+ */
+static int __init inotify_setup(void)
+{
+	atomic_set(&inotify_cookie, 0);
+
+	return 0;
+}
+
+module_init(inotify_setup);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
new file mode 100644
index 000000000000..400f8064a548
--- /dev/null
+++ b/fs/notify/inotify/inotify_user.c
@@ -0,0 +1,778 @@
+/*
+ * 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 <linux/magic.h>
+
+#include <asm/ioctls.h>
+
+static struct kmem_cache *watch_cachep __read_mostly;
+static struct kmem_cache *event_cachep __read_mostly;
+
+static struct vfsmount *inotify_mnt __read_mostly;
+
+/* these are configurable via /proc/sys/fs/inotify/ */
+static int inotify_max_user_instances __read_mostly;
+static int inotify_max_user_watches __read_mostly;
+static 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 */
+	struct user_struct	*user;		/* user who opened this dev */
+	struct inotify_handle	*ih;		/* inotify handle */
+	struct fasync_struct    *fa;            /* async notification */
+	atomic_t		count;		/* reference count */
+	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_NOFS);
+	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_get_last_event - return the last event in the given dev's queue
+ *
+ * Caller must hold dev->ev_mutex.
+ */
+static inline struct inotify_kernel_event *
+inotify_dev_get_last_event(struct inotify_device *dev)
+{
+	if (list_empty(&dev->events))
+		return NULL;
+	return list_entry(dev->events.prev, 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 inode *ignored)
+{
+	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 || w->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_last_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);
+	kill_fasync(&dev->fa, SIGIO, POLL_IN);
+
+out:
+	mutex_unlock(&dev->ev_mutex);
+}
+
+/*
+ * remove_kevent - cleans up 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;
+}
+
+/*
+ * free_kevent - frees the given kevent.
+ */
+static void free_kevent(struct inotify_kernel_event *kevent)
+{
+	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);
+		free_kevent(kevent);
+	}
+}
+
+/*
+ * find_inode - resolve a user-given path to a specific inode
+ */
+static int find_inode(const char __user *dirname, struct path *path,
+		      unsigned flags)
+{
+	int error;
+
+	error = user_path_at(AT_FDCWD, dirname, flags, path);
+	if (error)
+		return error;
+	/* you can only watch an inode if you have read permissions on it */
+	error = inode_permission(path->dentry->d_inode, MAY_READ);
+	if (error)
+		path_put(path);
+	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);
+
+	inotify_init_watch(&watch->wdata);
+	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) {
+
+		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);
+
+		mutex_lock(&dev->ev_mutex);
+		if (!list_empty(&dev->events)) {
+			ret = 0;
+			break;
+		}
+		mutex_unlock(&dev->ev_mutex);
+
+		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;
+
+	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) {
+			if (ret == 0 && count > 0) {
+				/*
+				 * could not get a single event because we
+				 * didn't have enough buffer space.
+				 */
+				ret = -EINVAL;
+			}
+			break;
+		}
+		remove_kevent(dev, kevent);
+
+		/*
+		 * Must perform the copy_to_user outside the mutex in order
+		 * to avoid a lock order reversal with mmap_sem.
+		 */
+		mutex_unlock(&dev->ev_mutex);
+
+		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;
+		}
+
+		free_kevent(kevent);
+
+		mutex_lock(&dev->ev_mutex);
+	}
+	mutex_unlock(&dev->ev_mutex);
+
+	return ret;
+}
+
+static int inotify_fasync(int fd, struct file *file, int on)
+{
+	struct inotify_device *dev = file->private_data;
+
+	return fasync_helper(fd, file, on, &dev->fa) >= 0 ? 0 : -EIO;
+}
+
+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,
+	.fasync         = inotify_fasync,
+	.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_init1(int flags)
+{
+	struct inotify_device *dev;
+	struct inotify_handle *ih;
+	struct user_struct *user;
+	struct file *filp;
+	int fd, ret;
+
+	/* Check the IN_* constants for consistency.  */
+	BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
+	BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
+
+	if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
+		return -EINVAL;
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	filp = get_empty_filp();
+	if (!filp) {
+		ret = -ENFILE;
+		goto out_put_fd;
+	}
+
+	user = get_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 (IS_ERR(ih)) {
+		ret = PTR_ERR(ih);
+		goto out_free_dev;
+	}
+	dev->ih = ih;
+	dev->fa = NULL;
+
+	filp->f_op = &inotify_fops;
+	filp->f_path.mnt = mntget(inotify_mnt);
+	filp->f_path.dentry = dget(inotify_mnt->mnt_root);
+	filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
+	filp->f_mode = FMODE_READ;
+	filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
+	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_init(void)
+{
+	return sys_inotify_init1(0);
+}
+
+asmlinkage long sys_inotify_add_watch(int fd, const char __user *pathname, u32 mask)
+{
+	struct inode *inode;
+	struct inotify_device *dev;
+	struct path path;
+	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(pathname, &path, flags);
+	if (unlikely(ret))
+		goto fput_and_out;
+
+	/* inode held in place by reference to path; dev by fget on fd */
+	inode = path.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_put(&path);
+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 int
+inotify_get_sb(struct file_system_type *fs_type, int flags,
+	       const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	return get_sb_pseudo(fs_type, "inotify", NULL,
+			INOTIFYFS_SUPER_MAGIC, mnt);
+}
+
+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);
+	event_cachep = kmem_cache_create("inotify_event_cache",
+					 sizeof(struct inotify_kernel_event),
+					 0, SLAB_PANIC, NULL);
+
+	return 0;
+}
+
+module_init(inotify_user_setup);