Merge branch 'audit.b21' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current

* 'audit.b21' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current: (25 commits)
  [PATCH] make set_loginuid obey audit_enabled
  [PATCH] log more info for directory entry change events
  [PATCH] fix AUDIT_FILTER_PREPEND handling
  [PATCH] validate rule fields' types
  [PATCH] audit: path-based rules
  [PATCH] Audit of POSIX Message Queue Syscalls v.2
  [PATCH] fix se_sen audit filter
  [PATCH] deprecate AUDIT_POSSBILE
  [PATCH] inline more audit helpers
  [PATCH] proc_loginuid_write() uses simple_strtoul() on non-terminated array
  [PATCH] update of IPC audit record cleanup
  [PATCH] minor audit updates
  [PATCH] fix audit_krule_to_{rule,data} return values
  [PATCH] add filtering by ppid
  [PATCH] log ppid
  [PATCH] collect sid of those who send signals to auditd
  [PATCH] execve argument logging
  [PATCH] fix deadlocks in AUDIT_LIST/AUDIT_LIST_RULES
  [PATCH] audit_panic() is audit-internal
  [PATCH] inotify (5/5): update kernel documentation
  ...

Manual fixup of conflict in unclude/linux/inotify.h

27 files changed, 2961 insertions, 1033 deletions

diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.txt
index 6d501903f68e..59a919f16144 100644
--- a/Documentation/filesystems/inotify.txt
+++ b/Documentation/filesystems/inotify.txt
@@ -69,17 +69,135 @@ Prototypes:
 	int inotify_rm_watch (int fd, __u32 mask);
 
 
-(iii) Internal Kernel Implementation
+(iii) Kernel Interface
 
-Each inotify instance is associated with an inotify_device structure.
+Inotify's kernel API consists a set of functions for managing watches and an
+event callback.
+
+To use the kernel API, you must first initialize an inotify instance with a set
+of inotify_operations.  You are given an opaque inotify_handle, which you use
+for any further calls to inotify.
+
+    struct inotify_handle *ih = inotify_init(my_event_handler);
+
+You must provide a function for processing events and a function for destroying
+the inotify watch.
+
+    void handle_event(struct inotify_watch *watch, u32 wd, u32 mask,
+    	              u32 cookie, const char *name, struct inode *inode)
+
+	watch - the pointer to the inotify_watch that triggered this call
+	wd - the watch descriptor
+	mask - describes the event that occurred
+	cookie - an identifier for synchronizing events
+	name - the dentry name for affected files in a directory-based event
+	inode - the affected inode in a directory-based event
+
+    void destroy_watch(struct inotify_watch *watch)
+
+You may add watches by providing a pre-allocated and initialized inotify_watch
+structure and specifying the inode to watch along with an inotify event mask.
+You must pin the inode during the call.  You will likely wish to embed the
+inotify_watch structure in a structure of your own which contains other
+information about the watch.  Once you add an inotify watch, it is immediately
+subject to removal depending on filesystem events.  You must grab a reference if
+you depend on the watch hanging around after the call.
+
+    inotify_init_watch(&my_watch->iwatch);
+    inotify_get_watch(&my_watch->iwatch);	// optional
+    s32 wd = inotify_add_watch(ih, &my_watch->iwatch, inode, mask);
+    inotify_put_watch(&my_watch->iwatch);	// optional
+
+You may use the watch descriptor (wd) or the address of the inotify_watch for
+other inotify operations.  You must not directly read or manipulate data in the
+inotify_watch.  Additionally, you must not call inotify_add_watch() more than
+once for a given inotify_watch structure, unless you have first called either
+inotify_rm_watch() or inotify_rm_wd().
+
+To determine if you have already registered a watch for a given inode, you may
+call inotify_find_watch(), which gives you both the wd and the watch pointer for
+the inotify_watch, or an error if the watch does not exist.
+
+    wd = inotify_find_watch(ih, inode, &watchp);
+
+You may use container_of() on the watch pointer to access your own data
+associated with a given watch.  When an existing watch is found,
+inotify_find_watch() bumps the refcount before releasing its locks.  You must
+put that reference with:
+
+    put_inotify_watch(watchp);
+
+Call inotify_find_update_watch() to update the event mask for an existing watch.
+inotify_find_update_watch() returns the wd of the updated watch, or an error if
+the watch does not exist.
+
+    wd = inotify_find_update_watch(ih, inode, mask);
+
+An existing watch may be removed by calling either inotify_rm_watch() or
+inotify_rm_wd().
+
+    int ret = inotify_rm_watch(ih, &my_watch->iwatch);
+    int ret = inotify_rm_wd(ih, wd);
+
+A watch may be removed while executing your event handler with the following:
+
+    inotify_remove_watch_locked(ih, iwatch);
+
+Call inotify_destroy() to remove all watches from your inotify instance and
+release it.  If there are no outstanding references, inotify_destroy() will call
+your destroy_watch op for each watch.
+
+    inotify_destroy(ih);
+
+When inotify removes a watch, it sends an IN_IGNORED event to your callback.
+You may use this event as an indication to free the watch memory.  Note that
+inotify may remove a watch due to filesystem events, as well as by your request.
+If you use IN_ONESHOT, inotify will remove the watch after the first event, at
+which point you may call the final inotify_put_watch.
+
+(iv) Kernel Interface Prototypes
+
+	struct inotify_handle *inotify_init(struct inotify_operations *ops);
+
+	inotify_init_watch(struct inotify_watch *watch);
+
+	s32 inotify_add_watch(struct inotify_handle *ih,
+		              struct inotify_watch *watch,
+			      struct inode *inode, u32 mask);
+
+	s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
+			       struct inotify_watch **watchp);
+
+	s32 inotify_find_update_watch(struct inotify_handle *ih,
+				      struct inode *inode, u32 mask);
+
+	int inotify_rm_wd(struct inotify_handle *ih, u32 wd);
+
+	int inotify_rm_watch(struct inotify_handle *ih,
+			     struct inotify_watch *watch);
+
+	void inotify_remove_watch_locked(struct inotify_handle *ih,
+					 struct inotify_watch *watch);
+
+	void inotify_destroy(struct inotify_handle *ih);
+
+	void get_inotify_watch(struct inotify_watch *watch);
+	void put_inotify_watch(struct inotify_watch *watch);
+
+
+(v) Internal Kernel Implementation
+
+Each inotify instance is represented by an inotify_handle structure.
+Inotify's userspace consumers also have an inotify_device which is
+associated with the inotify_handle, and on which events are queued.
 
 Each watch is associated with an inotify_watch structure.  Watches are chained
-off of each associated device and each associated inode.
+off of each associated inotify_handle and each associated inode.
 
-See fs/inotify.c for the locking and lifetime rules.
+See fs/inotify.c and fs/inotify_user.c for the locking and lifetime rules.
 
 
-(iv) Rationale
+(vi) Rationale
 
 Q: What is the design decision behind not tying the watch to the open fd of
    the watched object?
@@ -145,7 +263,7 @@ A: The poor user-space interface is the second biggest problem with dnotify.
    file descriptor-based one that allows basic file I/O and poll/select.
    Obtaining the fd and managing the watches could have been done either via a
    device file or a family of new system calls.  We decided to implement a
-   family of system calls because that is the preffered approach for new kernel
+   family of system calls because that is the preferred approach for new kernel
    interfaces.  The only real difference was whether we wanted to use open(2)
    and ioctl(2) or a couple of new system calls.  System calls beat ioctls.
 
diff --git a/fs/Kconfig b/fs/Kconfig
index 572cc435a1bb..20f9b557732d 100644
--- a/fs/Kconfig
+++ b/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
diff --git a/fs/Makefile b/fs/Makefile
index 078d3d1191a5..d0ea6bfccf29 100644
--- a/fs/Makefile
+++ b/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
 
diff --git a/fs/exec.c b/fs/exec.c
index 3a79d97ac234..d07858c0b7c4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -49,6 +49,7 @@
 #include <linux/rmap.h>
 #include <linux/acct.h>
 #include <linux/cn_proc.h>
+#include <linux/audit.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1085,6 +1086,11 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	/* kernel module loader fixup */
 	/* so we don't try to load run modprobe in kernel space. */
 	set_fs(USER_DS);
+
+	retval = audit_bprm(bprm);
+	if (retval)
+		return retval;
+
 	retval = -ENOENT;
 	for (try=0; try<2; try++) {
 		read_lock(&binfmt_lock);
diff --git a/fs/inotify.c b/fs/inotify.c
index 732ec4bd5774..723836a1f718 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -5,7 +5,10 @@
  *	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
@@ -20,35 +23,17 @@
 
 #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:
  *
@@ -56,327 +41,108 @@ int inotify_max_queued_events __read_mostly;
  * 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)
+ * 		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_device, inode, and
+ * Lifetimes of the three main data structures--inotify_handle, 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_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: 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().
+ * 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
- * create_watch() to put_inotify_watch().
+ * inotify_add_watch() to the final put_inotify_watch().
  */
 
 /*
- * struct inotify_device - represents an inotify instance
+ * struct inotify_handle - 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 inotify_handle {
 	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 */
+	const struct inotify_operations *in_ops; /* inotify caller operations */
 };
 
-/*
- * 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,
-		.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)
+static inline void get_inotify_handle(struct inotify_handle *ih)
 {
-	atomic_inc(&dev->count);
+	atomic_inc(&ih->count);
 }
 
-static inline void put_inotify_dev(struct inotify_device *dev)
+static inline void put_inotify_handle(struct inotify_handle *ih)
 {
-	if (atomic_dec_and_test(&dev->count)) {
-		atomic_dec(&dev->user->inotify_devs);
-		free_uid(dev->user);
-		idr_destroy(&dev->idr);
-		kfree(dev);
+	if (atomic_dec_and_test(&ih->count)) {
+		idr_destroy(&ih->idr);
+		kfree(ih);
 	}
 }
 
-static inline void get_inotify_watch(struct inotify_watch *watch)
+/**
+ * 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);
 
-/*
+/**
  * put_inotify_watch - decrements the ref count on a given watch.  cleans up
- * the watch and its references if the count reaches zero.
+ * watch references if the count reaches zero.  inotify_watch is freed by
+ * inotify callers via the destroy_watch() op.
+ * @watch: watch to release
  */
-static inline void put_inotify_watch(struct inotify_watch *watch)
+void put_inotify_watch(struct inotify_watch *watch)
 {
 	if (atomic_dec_and_test(&watch->count)) {
-		put_inotify_dev(watch->dev);
-		iput(watch->inode);
-		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->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 - add a new event to the given device
- *
- * Caller must hold dev->mutex.  Can sleep (calls kernel_event()).
- */
-static void inotify_dev_queue_event(struct inotify_device *dev,
-				    struct inotify_watch *watch, u32 mask,
-				    u32 cookie, const char *name)
-{
-	struct inotify_kernel_event *kevent, *last;
-
-	/* 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 == watch->wd &&
-			last->event.cookie == cookie) {
-		const char *lastname = last->name;
-
-		if (!name && !lastname)
-			return;
-		if (name && lastname && !strcmp(lastname, name))
-			return;
-	}
-
-	/* the queue overflowed and we already sent the Q_OVERFLOW event */
-	if (unlikely(dev->event_count > dev->max_events))
-		return;
-
-	/* 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(watch->wd, mask, cookie, name);
-
-	if (unlikely(!kevent))
-		return;
-
-	/* 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);
-}
-
-/*
- * remove_kevent - cleans up and ultimately frees the given kevent
- *
- * Caller must hold dev->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);
-}
+		struct inotify_handle *ih = watch->ih;
 
-/*
- * inotify_dev_event_dequeue - destroy an event on the given device
- *
- * Caller must hold dev->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);
+		iput(watch->inode);
+		ih->in_ops->destroy_watch(watch);
+		put_inotify_handle(ih);
 	}
 }
+EXPORT_SYMBOL_GPL(put_inotify_watch);
 
 /*
- * inotify_dev_get_wd - returns the next WD for use by the given dev
+ * inotify_handle_get_wd - returns the next WD for use by the given handle
  *
- * Callers must hold dev->mutex.  This function can sleep.
+ * Callers must hold ih->mutex.  This function can sleep.
  */
-static int inotify_dev_get_wd(struct inotify_device *dev,
-			      struct inotify_watch *watch)
+static int inotify_handle_get_wd(struct inotify_handle *ih,
+				 struct inotify_watch *watch)
 {
 	int ret;
 
 	do {
-		if (unlikely(!idr_pre_get(&dev->idr, GFP_KERNEL)))
+		if (unlikely(!idr_pre_get(&ih->idr, GFP_KERNEL)))
 			return -ENOSPC;
-		ret = idr_get_new_above(&dev->idr, watch, dev->last_wd+1, &watch->wd);
+		ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
 	} while (ret == -EAGAIN);
 
-	return ret;
-}
+	if (likely(!ret))
+		ih->last_wd = watch->wd;
 
-/*
- * 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;
+	return ret;
 }
 
 /*
@@ -422,67 +188,18 @@ static void set_dentry_child_flags(struct inode *inode, int watched)
 }
 
 /*
- * create_watch - creates a watch on the given device.
- *
- * Callers must hold dev->mutex.  Calls inotify_dev_get_wd() so may sleep.
- * Both 'dev' and 'inode' (by way of nameidata) need to be pinned.
- */
-static struct inotify_watch *create_watch(struct inotify_device *dev,
-					  u32 mask, struct inode *inode)
-{
-	struct inotify_watch *watch;
-	int ret;
-
-	if (atomic_read(&dev->user->inotify_watches) >=
-			inotify_max_user_watches)
-		return ERR_PTR(-ENOSPC);
-
-	watch = kmem_cache_alloc(watch_cachep, GFP_KERNEL);
-	if (unlikely(!watch))
-		return ERR_PTR(-ENOMEM);
-
-	ret = inotify_dev_get_wd(dev, watch);
-	if (unlikely(ret)) {
-		kmem_cache_free(watch_cachep, watch);
-		return ERR_PTR(ret);
-	}
-
-	dev->last_wd = watch->wd;
-	watch->mask = mask;
-	atomic_set(&watch->count, 0);
-	INIT_LIST_HEAD(&watch->d_list);
-	INIT_LIST_HEAD(&watch->i_list);
-
-	/* save a reference to device and bump the count to make it official */
-	get_inotify_dev(dev);
-	watch->dev = dev;
-
-	/*
-	 * 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);
-
-	/* bump our own count, corresponding to our entry in dev->watches */
-	get_inotify_watch(watch);
-
-	atomic_inc(&dev->user->inotify_watches);
-
-	return watch;
-}
-
-/*
- * inotify_find_dev - find the watch associated with the given inode and dev
+ * 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_dev(struct inode *inode,
-					    struct inotify_device *dev)
+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->dev == dev)
+		if (watch->ih == ih)
 			return watch;
 	}
 
@@ -490,40 +207,40 @@ static struct inotify_watch *inode_find_dev(struct inode *inode,
 }
 
 /*
- * remove_watch_no_event - remove_watch() without the IN_IGNORED event.
+ * 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_device *dev)
+				  struct inotify_handle *ih)
 {
 	list_del(&watch->i_list);
-	list_del(&watch->d_list);
+	list_del(&watch->h_list);
 
 	if (!inotify_inode_watched(watch->inode))
 		set_dentry_child_flags(watch->inode, 0);
 
-	atomic_dec(&dev->user->inotify_watches);
-	idr_remove(&dev->idr, watch->wd);
-	put_inotify_watch(watch);
+	idr_remove(&ih->idr, watch->wd);
 }
 
-/*
- * remove_watch - Remove a watch from both the device and the inode.  Sends
- * the IN_IGNORED event to the given device signifying that the inode is no
- * longer watched.
- *
- * Callers must hold both inode->inotify_mutex and dev->mutex.  We drop a
- * reference to the inode before returning.
+/**
+ * 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
  *
- * The inode is not iput() so as to remain atomic.  If the inode needs to be
- * iput(), the call returns one.  Otherwise, it returns zero.
+ * Callers must hold both inode->inotify_mutex and ih->mutex.
  */
-static void remove_watch(struct inotify_watch *watch,struct inotify_device *dev)
+void inotify_remove_watch_locked(struct inotify_handle *ih,
+				 struct inotify_watch *watch)
 {
-	inotify_dev_queue_event(dev, watch, IN_IGNORED, 0, NULL);
-	remove_watch_no_event(watch, dev);
+	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 */
+/* Kernel API for producing events */
 
 /*
  * inotify_d_instantiate - instantiate dcache entry for inode
@@ -563,9 +280,10 @@ void inotify_d_move(struct dentry *entry)
  * @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)
+			       const char *name, struct inode *n_inode)
 {
 	struct inotify_watch *watch, *next;
 
@@ -576,14 +294,13 @@ void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
 	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
 		u32 watch_mask = watch->mask;
 		if (watch_mask & mask) {
-			struct inotify_device *dev = watch->dev;
-			get_inotify_watch(watch);
-			mutex_lock(&dev->mutex);
-			inotify_dev_queue_event(dev, watch, mask, cookie, name);
+			struct inotify_handle *ih= watch->ih;
+			mutex_lock(&ih->mu