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

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.
 

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/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);

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->mutex);
 			if (watch_mask & IN_ONESHOT)
-				remove_watch_no_event(watch, dev);
-			mutex_unlock(&dev->mutex);
-			put_inotify_watch(watch);
+				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);
@@ -613,7 +330,8 @@ void inotify_dentry_parent_queue_event(struct dentry *dentry, u32 mask,
 	if (inotify_inode_watched(inode)) {
 		dget(parent);
 		spin_unlock(&dentry->d_lock);
-		inotify_inode_queue_event(inode, mask, cookie, name);
+		inotify_inode_queue_event(inode, mask, cookie, name,
+					  dentry->d_inode);
 		dput(parent);
 	} else
 		spin_unlock(&dentry->d_lock);
@@ -665,7 +383,7 @@ void inotify_unmount_inodes(struct list_head *list)
 
 		need_iput_tmp = need_iput;
 		need_iput = NULL;
-		/* In case the remove_watch() drops a reference. */
+		/* In case inotify_remove_watch_locked() drops a reference. */
 		if (inode != need_iput_tmp)
 			__iget(inode);
 		else
@@ -694,11 +412,12 @@ void inotify_unmount_inodes(struct list_head *list)
 		mutex_lock(&inode->inotify_mutex);
 		watches = &inode->inotify_watches;
 		list_for_each_entry_safe(watch, next_w, watches, i_list) {
-			struct inotify_device *dev = watch->dev;
-			mutex_lock(&dev->mutex);
-			inotify_dev_queue_event(dev, watch, IN_UNMOUNT,0,NULL);
-			remove_watch(watch, dev);
-			mutex_unlock(&dev->mutex);
+			struct inotify_handle *ih= watch->ih;
+			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);
 		}
 		mutex_unlock(&inode->inotify_mutex);
 		iput(inode);		
@@ -718,432 +437,292 @@ void inotify_inode_is_dead(struct inode *inode)
 
 	mutex_lock(&inode->inotify_mutex);
 	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
-		struct inotify_device *dev = watch->dev;
-		mutex_lock(&dev->mutex);
-		remove_watch(watch, dev);
-		mutex_unlock(&dev->mutex);
+		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);
 
-/* Device Interface */
+/* Kernel Consumer API */
 
-static unsigned int inotify_poll(struct file *file, poll_table *wait)
+/**
+ * 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_device *dev = file->private_data;
-	int ret = 0;
+	struct inotify_handle *ih;
 
-	poll_wait(file, &dev->wq, wait);
-	mutex_lock(&dev->mutex);
-	if (!list_empty(&dev->events))
-		ret = POLLIN | POLLRDNORM;
-	mutex_unlock(&dev->mutex);
+	ih = kmalloc(sizeof(struct inotify_handle), GFP_KERNEL);
+	if (unlikely(!ih))
+		return ERR_PTR(-ENOMEM);
 
-	return ret;
+	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);
 
-static ssize_t inotify_read(struct file *file, char __user *buf,
-			    size_t count, loff_t *pos)
+/**
+ * inotify_init_watch - initialize an inotify watch
+ * @watch: watch to initialize
+ */
+void inotify_init_watch(struct inotify_watch *watch)
 {
-	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->mutex);
-		events = !list_empty(&dev->events);
-		mutex_unlock(&dev->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->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->mutex);
-
-	return ret;
+	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);
 
-static int inotify_release(struct inode *ignored, struct file *file)
+/**
+ * inotify_destroy - clean up and destroy an inotify instance
+ * @ih: inotify handle
+ */
+void inotify_destroy(struct inotify_handle *ih)
 {
-	struct inotify_device *dev = file->private_data;
-
 	/*
-	 * Destroy all of the watches on this device.  Unfortunately, not very
+	 * 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 dev->mutex.  The following works.
+	 * hold inode->inotify_mutex before ih->mutex.  The following works.
 	 */
 	while (1) {
 		struct inotify_watch *watch;
 		struct list_head *watches;
 		struct inode *inode;
 
-		mutex_lock(&dev->mutex);
-		watches = &dev->watches;
+		mutex_lock(&ih->mutex);
+		watches = &ih->watches;
 		if (list_empty(watches)) {
-			mutex_unlock(&dev->mutex);
+			mutex_unlock(&ih->mutex);
 			break;
 		}
-		watch = list_entry(watches->next, struct inotify_watch, d_list);
+		watch = list_entry(watches->next, struct inotify_watch, h_list);
 		get_inotify_watch(watch);
-		mutex_unlock(&dev->mutex);
+		mutex_unlock(&ih->mutex);
 
 		inode = watch->inode;
 		mutex_lock(&inode->inotify_mutex);
-		mutex_lock(&dev->mutex);
+		mutex_lock(&ih->mutex);
 
 		/* make sure we didn't race with another list removal */
-		if (likely(idr_find(&dev->idr, watch->wd)))
-			remove_watch_no_event(watch, dev);
+		if (likely(idr_find(&ih->idr, watch->wd))) {
+			remove_watch_no_event(watch, ih);
+			put_inotify_watch(watch);
+		}
 
-		mutex_unlock(&dev->mutex);
+		mutex_unlock(&ih->mutex);
 		mutex_unlock(&inode->inotify_mutex);
 		put_inotify_watch(watch);
 	}
 
-	/* destroy all of the events on this device */
-	mutex_lock(&dev->mutex);
-	while (!list_empty(&dev->events))
-		inotify_dev_event_dequeue(dev);
-	mutex_unlock(&dev->mutex);
-
-	/* free this device: the put matching the get in inotify_init() */
-	put_inotify_dev(dev);
-
-	return 0;
+	/* free this handle: the put matching the get in inotify_init() */
+	put_inotify_handle(ih);
 }
+EXPORT_SYMBOL_GPL(inotify_destroy);
 
-/*
- * inotify_ignore - remove a given wd from this inotify instance.
+/**
+ * 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
  *
- * Can sleep.
+ * Caller must pin given inode (via nameidata).
  */
-static int inotify_ignore(struct inotify_device *dev, s32 wd)
+s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
+		       struct inotify_watch **watchp)
 {
-	struct inotify_watch *watch;
-	struct inode *inode;
-
-	mutex_lock(&dev->mutex);
-	watch = idr_find(&dev->idr, wd);
-	if (unlikely(!watch)) {
-		mutex_unlock(&dev->mutex);
-		return -EINVAL;
-	}
-	get_inotify_watch(watch);
-	inode = watch->inode;
-	mutex_unlock(&dev->mutex);
+	struct inotify_watch *old;
+	int ret = -ENOENT;
 
 	mutex_lock(&inode->inotify_mutex);
-	mutex_lock(&dev->mutex);
+	mutex_lock(&ih->mutex);
 
-	/* make sure that we did not race */
-	if (likely(idr_find(&dev->idr, wd) == watch))
-		remove_watch(watch, dev);
+	old = inode_find_handle(inode, ih);
+	if (unlikely(old)) {
+		get_inotify_watch(old); /* caller must put watch */
+		*watchp = old;
+		ret = old->wd;
+	}
 
-	mutex_unlock(&dev->mutex);
+	mutex_unlock(&ih->mutex);
 	mutex_unlock(&inode->inotify_mutex);
-	put_inotify_watch(watch);
 
-	return 0;
+	return ret;
 }
+EXPORT_SYMBOL_GPL(inotify_find_watch);
 
-static long inotify_ioctl(struct file *file, unsigned int cmd,
-			  unsigned long arg)
+/**
+ * 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_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;
-}
+	struct inotify_watch *old;
+	int mask_add = 0;
+	int 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,
-};
+	if (mask & IN_MASK_ADD)
+		mask_add = 1;
 
-asmlinkage long sys_inotify_init(void)
-{
-	struct inotify_device *dev;
-	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;
-	}
+	/* don't allow invalid bits: we don't want flags set */
+	mask &= IN_ALL_EVENTS | IN_ONESHOT;
+	if (unlikely(!mask))
+		return -EINVAL;
 
-	user = get_uid(current->user);
-	if (unlikely(atomic_read(&user->inotify_devs) >=
-			inotify_max_user_instances)) {
-		ret = -EMFILE;
-		goto out_free_uid;
-	}
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
 
-	dev = kmalloc(sizeof(struct inotify_device), GFP_KERNEL);
-	if (unlikely(!dev)) {
-		ret = -ENOMEM;
-		goto out_free_uid;
+	/*
+	 * 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;
 	}
 
-	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;
-
-	idr_init(&dev->idr);
-	INIT_LIST_HEAD(&dev->events);
-	INIT_LIST_HEAD(&dev->watches);
-	init_waitqueue_head(&dev->wq);
-	mutex_init(&dev->mutex);
-	dev->event_count = 0;
-	dev->queue_size = 0;
-	dev->max_events = inotify_max_queued_events;
-	dev->user = user;
-	dev->last_wd = 0;
-	atomic_set(&dev->count, 0);
-
-	get_inotify_dev(dev);
-	atomic_inc(&user->inotify_devs);
-	fd_install(fd, filp);
-
-	return fd;
-out_free_uid:
-	free_uid(user);
-	put_filp(filp);
-out_put_fd:
-	put_unused_fd(fd);
+	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);
 
-asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
+/**
+ * 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)
 {
-	struct inotify_watch *watch, *old;
-	struct inode *inode;
-	struct inotify_device *dev;
-	struct nameidata nd;
-	struct file *filp;
-	int ret, fput_needed;
-	int mask_add = 0;
-	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;
+	int ret = 0;
 
-	/* inode held in place by reference to nd; dev by fget on fd */
-	inode = nd.dentry->d_inode;
-	dev = filp->private_data;
+	/* 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(&dev->mutex);
-
-	if (mask & IN_MASK_ADD)
-		mask_add = 1;
+	mutex_lock(&ih->mutex);
 
-	/* don't let user-space set invalid bits: we don't want flags set */
-	mask &= IN_ALL_EVENTS | IN_ONESHOT;
-	if (unlikely(!mask)) {
-		ret = -EINVAL;
+	/* 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;
 
 	/*
-	 * Handle the case of re-adding a watch on an (inode,dev) pair that we
-	 * are already watching.  We just update the mask and return its wd.
+	 * 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.
 	 */
-	old = inode_find_dev(inode, dev);
-	if (unlikely(old)) {
-		if (mask_add)
-			old->mask |= mask;
-		else
-			old->mask = mask;
-		ret = old->wd;
-		goto out;
-	}
-
-	watch = create_watch(dev, mask, inode);
-	if (unlikely(IS_ERR(watch))) {
-		ret = PTR_ERR(watch);
-		goto out;
-	}
+	watch->inode = igrab(inode);
 
 	if (!inotify_inode_watched(inode))
 		set_dentry_child_flags(inode, 1);
 
-	/* Add the watch to the device's and the inode's list */
-	list_add(&watch->d_list, &dev->watches);
+	/* Add the watch to the handle's and the inode's list */
+	list_add(&watch->h_list, &ih->watches);
 	list_add(&watch->i_list, &inode->inotify_watches);
-	ret = watch->wd;
 out:
-	mutex_unlock(&dev->mutex);
+	mutex_unlock(&ih->mutex);
 	mutex_unlock(&inode->inotify_mutex);
-	path_release(&nd);
-fput_and_out:
-	fput_light(filp, fput_needed);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(inotify_add_watch);
 
-asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
+/**
+ * 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 file *filp;
-	struct inotify_device *dev;
-	int ret, fput_needed;
-
-	filp = fget_light(fd, &fput_needed);
-	if (unlikely(!filp))
-		return -EBADF;
+	struct inotify_watch *watch;
+	struct inode *inode;
 
-	/* verify that this is indeed an inotify instance */
-	if (unlikely(filp->f_op != &inotify_fops)) {
-		ret = -EINVAL;
-		goto out;
+	mutex_lock(&ih->mutex);
+	watch = idr_find(&ih->idr, wd);
+	if (unlikely(!watch)) {
+		mutex_unlock(&ih->mutex);
+		return -EINVAL;
 	}
+	get_inotify_watch(watch);
+	inode = watch->inode;
+	mutex_unlock(&ih->mutex);
 
-	dev = filp->private_data;
-	ret = inotify_ignore(dev, wd);
+	mutex_lock(&inode->inotify_mutex);
+	mutex_lock(&ih->mutex);
 
-out:
-	fput_light(filp, fput_needed);
-	return ret;
+	/* 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);
+	put_inotify_watch(watch);
+
+	return 0;
 }
+EXPORT_SYMBOL_GPL(inotify_rm_wd);
 
-static struct super_block *
-inotify_get_sb(struct file_system_type *fs_type, int flags,
-	       const char *dev_name, void *data)
+/**
+ * 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 get_sb_pseudo(fs_type, "inotify", NULL, 0xBAD1DEA);
+	return inotify_rm_wd(ih, watch->wd);
 }
-
-static struct file_system_type inotify_fs_type = {
-    .name           = "inotifyfs",
-    .get_sb         = inotify_get_sb,
-    .kill_sb        = kill_anon_super,
-};
+EXPORT_SYMBOL_GPL(inotify_rm_watch);
 
 /*
- * inotify_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().
+ * inotify_setup - core initialization function
  */
 static int __init inotify_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;
-
 	atomic_set(&inotify_cookie, 0);
 
-	watch_cachep = kmem_cache_create("inotify_watch_cache",
-					 sizeof(struct inotify_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;
 }
 

fs/inotify_user.c

@@ -0,0 +1,719 @@
+/*
+ * 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 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 || 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);
+
+	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) {
+		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);

fs/namei.c

@@ -1127,7 +1127,7 @@ out:
 	if (likely(retval == 0)) {
 		if (unlikely(current->audit_context && nd && nd->dentry &&
 				nd->dentry->d_inode))
-		audit_inode(name, nd->dentry->d_inode, flags);
+		audit_inode(name, nd->dentry->d_inode);
 	}
 out_fail:
 	return retval;

fs/open.c

@@ -633,7 +633,7 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
 	dentry = file->f_dentry;
 	inode = dentry->d_inode;
 
-	audit_inode(NULL, inode, 0);
+	audit_inode(NULL, inode);
 
 	err = -EROFS;
 	if (IS_RDONLY(inode))
@@ -786,7 +786,7 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
 	if (file) {
 		struct dentry * dentry;
 		dentry = file->f_dentry;
-		audit_inode(NULL, dentry->d_inode, 0);
+		audit_inode(NULL, dentry->d_inode);
 		error = chown_common(dentry, user, group);
 		fput(file);
 	}

fs/proc/base.c

@@ -1019,8 +1019,8 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 	if (current != task)
 		return -EPERM;
 
-	if (count > PAGE_SIZE)
-		count = PAGE_SIZE;
+	if (count >= PAGE_SIZE)
+		count = PAGE_SIZE - 1;
 
 	if (*ppos != 0) {
 		/* No partial writes. */
@@ -1033,6 +1033,7 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 	if (copy_from_user(page, buf, count))
 		goto out_free_page;
 
+	page[count] = '\0';
 	loginuid = simple_strtoul(page, &tmp, 10);
 	if (tmp == page) {
 		length = -EINVAL;

fs/xattr.c

@@ -242,7 +242,7 @@ sys_fsetxattr(int fd, char __user *name, void __user *value,
 	if (!f)
 		return error;
 	dentry = f->f_dentry;
-	audit_inode(NULL, dentry->d_inode, 0);
+	audit_inode(NULL, dentry->d_inode);
 	error = setxattr(dentry, name, value, size, flags);
 	fput(f);
 	return error;
@@ -469,7 +469,7 @@ sys_fremovexattr(int fd, char __user *name)
 	if (!f)
 		return error;
 	dentry = f->f_dentry;
-	audit_inode(NULL, dentry->d_inode, 0);
+	audit_inode(NULL, dentry->d_inode);
 	error = removexattr(dentry, name);
 	fput(f);
 	return error;

include/linux/audit.h

@@ -82,7 +82,12 @@
 #define AUDIT_CONFIG_CHANGE	1305	/* Audit system configuration change */
 #define AUDIT_SOCKADDR		1306	/* sockaddr copied as syscall arg */
 #define AUDIT_CWD		1307	/* Current working directory */
+#define AUDIT_EXECVE		1309	/* execve arguments */
 #define AUDIT_IPC_SET_PERM	1311	/* IPC new permissions record type */
+#define AUDIT_MQ_OPEN		1312	/* POSIX MQ open record type */
+#define AUDIT_MQ_SENDRECV	1313	/* POSIX MQ send/receive record type */
+#define AUDIT_MQ_NOTIFY		1314	/* POSIX MQ notify record type */
+#define AUDIT_MQ_GETSETATTR	1315	/* POSIX MQ get/set attribute record type */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
@@ -150,6 +155,7 @@
 #define AUDIT_SE_TYPE	15	/* security label type */
 #define AUDIT_SE_SEN	16	/* security label sensitivity label */
 #define AUDIT_SE_CLR	17	/* security label clearance label */
+#define AUDIT_PPID	18
 
 				/* These are ONLY useful when checking
 				 * at syscall exit time (AUDIT_AT_EXIT). */
@@ -158,6 +164,7 @@
 #define AUDIT_INODE	102
 #define AUDIT_EXIT	103
 #define AUDIT_SUCCESS   104	/* exit >= 0; value ignored */
+#define AUDIT_WATCH	105
 
 #define AUDIT_ARG0      200
 #define AUDIT_ARG1      (AUDIT_ARG0+1)
@@ -277,12 +284,16 @@ struct audit_rule {		/* for AUDIT_LIST, AUDIT_ADD, and AUDIT_DEL */
 struct audit_sig_info {
 	uid_t		uid;
 	pid_t		pid;
+	char		ctx[0];
 };
 
 struct audit_buffer;
 struct audit_context;
 struct inode;
 struct netlink_skb_parms;
+struct linux_binprm;
+struct mq_attr;
+struct mqstat;
 
 #define AUDITSC_INVALID 0
 #define AUDITSC_SUCCESS 1
@@ -297,15 +308,19 @@ extern void audit_syscall_entry(int arch,
 				int major, unsigned long a0, unsigned long a1,
 				unsigned long a2, unsigned long a3);
 extern void audit_syscall_exit(int failed, long return_code);
-extern void audit_getname(const char *name);
+extern void __audit_getname(const char *name);
 extern void audit_putname(const char *name);
-extern void __audit_inode(const char *name, const struct inode *inode, unsigned flags);
+extern void __audit_inode(const char *name, const struct inode *inode);
 extern void __audit_inode_child(const char *dname, const struct inode *inode,
 				unsigned long pino);
-static inline void audit_inode(const char *name, const struct inode *inode,
-			       unsigned flags) {
+static inline void audit_getname(const char *name)
+{
 	if (unlikely(current->audit_context))
-		__audit_inode(name, inode, flags);
+		__audit_getname(name);
+}
+static inline void audit_inode(const char *name, const struct inode *inode) {
+	if (unlikely(current->audit_context))
+		__audit_inode(name, inode);
 }
 static inline void audit_inode_child(const char *dname, 
 				     const struct inode *inode, 
@@ -320,13 +335,61 @@ extern void auditsc_get_stamp(struct audit_context *ctx,
 			      struct timespec *t, unsigned int *serial);
 extern int  audit_set_loginuid(struct task_struct *task, uid_t loginuid);
 extern uid_t audit_get_loginuid(struct audit_context *ctx);
-extern int audit_ipc_obj(struct kern_ipc_perm *ipcp);
-extern int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode, struct kern_ipc_perm *ipcp);
+extern int __audit_ipc_obj(struct kern_ipc_perm *ipcp);
+extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode);
+extern int audit_bprm(struct linux_binprm *bprm);
 extern int audit_socketcall(int nargs, unsigned long *args);
 extern int audit_sockaddr(int len, void *addr);
 extern int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt);
-extern void audit_signal_info(int sig, struct task_struct *t);
 extern int audit_set_macxattr(const char *name);
+extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr);
+extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout);
+extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout);
+extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification);
+extern int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
+
+static inline int audit_ipc_obj(struct kern_ipc_perm *ipcp)
+{
+	if (unlikely(current->audit_context))
+		return __audit_ipc_obj(ipcp);
+	return 0;
+}
+static inline int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
+{
+	if (unlikely(current->audit_context))
+		return __audit_ipc_set_perm(qbytes, uid, gid, mode);
+	return 0;
+}
+static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
+{
+	if (unlikely(current->audit_context))
+		return __audit_mq_open(oflag, mode, u_attr);
+	return 0;
+}
+static inline int audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout)
+{
+	if (unlikely(current->audit_context))
+		return __audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout);
+	return 0;
+}
+static inline int audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout)
+{
+	if (unlikely(current->audit_context))
+		return __audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
+	return 0;
+}
+static inline int audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
+{
+	if (unlikely(current->audit_context))
+		return __audit_mq_notify(mqdes, u_notification);
+	return 0;
+}
+static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
+{
+	if (unlikely(current->audit_context))
+		return __audit_mq_getsetattr(mqdes, mqstat);
+	return 0;
+}
 #else
 #define audit_alloc(t) ({ 0; })
 #define audit_free(t) do { ; } while (0)
@@ -334,19 +397,24 @@ extern int audit_set_macxattr(const char *name);
 #define audit_syscall_exit(f,r) do { ; } while (0)
 #define audit_getname(n) do { ; } while (0)
 #define audit_putname(n) do { ; } while (0)
-#define __audit_inode(n,i,f) do { ; } while (0)
+#define __audit_inode(n,i) do { ; } while (0)
 #define __audit_inode_child(d,i,p) do { ; } while (0)
-#define audit_inode(n,i,f) do { ; } while (0)
+#define audit_inode(n,i) do { ; } while (0)
 #define audit_inode_child(d,i,p) do { ; } while (0)
 #define auditsc_get_stamp(c,t,s) do { BUG(); } while (0)
 #define audit_get_loginuid(c) ({ -1; })
 #define audit_ipc_obj(i) ({ 0; })
-#define audit_ipc_set_perm(q,u,g,m,i) ({ 0; })
+#define audit_ipc_set_perm(q,u,g,m) ({ 0; })
+#define audit_bprm(p) ({ 0; })
 #define audit_socketcall(n,a) ({ 0; })
 #define audit_sockaddr(len, addr) ({ 0; })
 #define audit_avc_path(dentry, mnt) ({ 0; })
-#define audit_signal_info(s,t) do { ; } while (0)
 #define audit_set_macxattr(n) do { ; } while (0)
+#define audit_mq_open(o,m,a) ({ 0; })
+#define audit_mq_timedsend(d,l,p,t) ({ 0; })
+#define audit_mq_timedreceive(d,l,p,t) ({ 0; })
+#define audit_mq_notify(d,n) ({ 0; })
+#define audit_mq_getsetattr(d,s) ({ 0; })
 #endif
 
 #ifdef CONFIG_AUDIT
@@ -364,8 +432,11 @@ extern void		    audit_log_end(struct audit_buffer *ab);
 extern void		    audit_log_hex(struct audit_buffer *ab,
 					  const unsigned char *buf,
 					  size_t len);
-extern void		    audit_log_untrustedstring(struct audit_buffer *ab,
+extern const char *	    audit_log_untrustedstring(struct audit_buffer *ab,
 						      const char *string);
+extern const char *	    audit_log_n_untrustedstring(struct audit_buffer *ab,
+							size_t n,
+							const char *string);
 extern void		    audit_log_d_path(struct audit_buffer *ab,
 					     const char *prefix,
 					     struct dentry *dentry,
@@ -383,8 +454,8 @@ extern int  audit_receive_filter(int type, int pid, int uid, int seq,
 #define audit_log_end(b) do { ; } while (0)
 #define audit_log_hex(a,b,l) do { ; } while (0)
 #define audit_log_untrustedstring(a,s) do { ; } while (0)
+#define audit_log_n_untrustedstring(a,n,s) do { ; } while (0)
 #define audit_log_d_path(b,p,d,v) do { ; } while (0)
-#define audit_panic(m) do { ; } while (0)
 #endif
 #endif
 #endif

include/linux/fsnotify.h

@@ -54,19 +54,20 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 
 	if (isdir)
 		isdir = IN_ISDIR;
-	inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name);
-	inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name);
+	inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name,
+				  source);
+	inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name,
+				  source);
 
 	if (target) {
-		inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL);
+		inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL, NULL);
 		inotify_inode_is_dead(target);
 	}
 
 	if (source) {
-		inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL);
+		inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL);
 	}
-	audit_inode_child(old_name, source, old_dir->i_ino);
-	audit_inode_child(new_name, target, new_dir->i_ino);
+	audit_inode_child(new_name, source, new_dir->i_ino);
 }
 
 /*
@@ -85,7 +86,7 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
  */
 static inline void fsnotify_inoderemove(struct inode *inode)
 {
-	inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL);
+	inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL);
 	inotify_inode_is_dead(inode);
 }
 
@@ -95,7 +96,8 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
 	inode_dir_notify(inode, DN_CREATE);
-	inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name);
+	inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name,
+				  dentry->d_inode);
 	audit_inode_child(dentry->d_name.name, dentry->d_inode, inode->i_ino);
 }
 
@@ -106,7 +108,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
 	inode_dir_notify(inode, DN_CREATE);
 	inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, 
-				  dentry->d_name.name);
+				  dentry->d_name.name, dentry->d_inode);
 	audit_inode_child(dentry->d_name.name, dentry->d_inode, inode->i_ino);
 }
 
@@ -123,7 +125,7 @@ static inline void fsnotify_access(struct dentry *dentry)
 
 	dnotify_parent(dentry, DN_ACCESS);
 	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-	inotify_inode_queue_event(inode, mask, 0, NULL);
+	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
 }
 
 /*
@@ -139,7 +141,7 @@ static inline void fsnotify_modify(struct dentry *dentry)
 
 	dnotify_parent(dentry, DN_MODIFY);
 	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-	inotify_inode_queue_event(inode, mask, 0, NULL);
+	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
 }
 
 /*
@@ -154,7 +156,7 @@ static inline void fsnotify_open(struct dentry *dentry)
 		mask |= IN_ISDIR;
 
 	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-	inotify_inode_queue_event(inode, mask, 0, NULL);	
+	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
 }
 
 /*
@@ -172,7 +174,7 @@ static inline void fsnotify_close(struct file *file)
 		mask |= IN_ISDIR;
 
 	inotify_dentry_parent_queue_event(dentry, mask, 0, name);
-	inotify_inode_queue_event(inode, mask, 0, NULL);
+	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
 }
 
 /*
@@ -187,7 +189,7 @@ static inline void fsnotify_xattr(struct dentry *dentry)
 		mask |= IN_ISDIR;
 
 	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
-	inotify_inode_queue_event(inode, mask, 0, NULL);
+	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
 }
 
 /*
@@ -234,7 +236,7 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 	if (in_mask) {
 		if (S_ISDIR(inode->i_mode))
 			in_mask |= IN_ISDIR;
-		inotify_inode_queue_event(inode, in_mask, 0, NULL);
+		inotify_inode_queue_event(inode, in_mask, 0, NULL, NULL);
 		inotify_dentry_parent_queue_event(dentry, in_mask, 0,
 						  dentry->d_name.name);
 	}

include/linux/inotify.h

@@ -68,18 +68,65 @@ 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 *, struct inode *);
+	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,
-				      const char *);
+				      const char *, struct inode *);
 extern void inotify_dentry_parent_queue_event(struct dentry *, __u32, __u32,
 					      const char *);
 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_init_watch(struct inotify_watch *);
+extern void inotify_destroy(struct inotify_handle *);
+extern __s32 inotify_find_watch(struct inotify_handle *, struct inode *,
+				struct inotify_watch **);
+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_watch(struct inotify_handle *, struct inotify_watch *);
+extern int inotify_rm_wd(struct inotify_handle *, __u32);
+extern void inotify_remove_watch_locked(struct inotify_handle *,
+					struct inotify_watch *);
+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,
@@ -93,7 +140,8 @@ static inline void inotify_d_move(struct dentry *dentry)
 
 static inline void inotify_inode_queue_event(struct inode *inode,
 					     __u32 mask, __u32 cookie,
-					     const char *filename)
+					     const char *filename,
+					     struct inode *n_inode)
 {
 }
 
@@ -116,6 +164,62 @@ 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_init_watch(struct inotify_watch *watch)
+{
+}
+
+static inline void inotify_destroy(struct inotify_handle *ih)
+{
+}
+
+static inline __s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
+				       struct inotify_watch **watchp)
+{
+	return -EOPNOTSUPP;
+}
+
+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_watch(struct inotify_handle *ih,
+				   struct inotify_watch *watch)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int inotify_rm_wd(struct inotify_handle *ih, __u32 wd)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void inotify_remove_watch_locked(struct inotify_handle *ih,
+					       struct inotify_watch *watch)
+{
+}
+
+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

init/Kconfig

@@ -182,7 +182,8 @@ config AUDITSYSCALL
 	help
 	  Enable low-overhead system-call auditing infrastructure that
 	  can be used independently or with another kernel subsystem,
-	  such as SELinux.
+	  such as SELinux.  To use audit's filesystem watch feature, please
+	  ensure that INOTIFY is configured.
 
 config IKCONFIG
 	bool "Kernel .config support"

ipc/mqueue.c

@@ -8,6 +8,8 @@
  * Lockless receive & send, fd based notify:
  * 			    Manfred Spraul	    (manfred@colorfullife.com)
  *
+ * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
+ *
  * This file is released under the GPL.
  */
 
@@ -24,6 +26,7 @@
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/syscalls.h>
+#include <linux/audit.h>
 #include <linux/signal.h>
 #include <linux/mutex.h>
 
@@ -657,6 +660,10 @@ asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode,
 	char *name;
 	int fd, error;
 
+	error = audit_mq_open(oflag, mode, u_attr);
+	if (error != 0)
+		return error;
+
 	if (IS_ERR(name = getname(u_name)))
 		return PTR_ERR(name);
 
@@ -814,6 +821,10 @@ asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
 	long timeout;
 	int ret;
 
+	ret = audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout);
+	if (ret != 0)
+		return ret;
+
 	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
 		return -EINVAL;
 
@@ -896,6 +907,10 @@ asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
 	struct mqueue_inode_info *info;
 	struct ext_wait_queue wait;
 
+	ret = audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
+	if (ret != 0)
+		return ret;
+
 	timeout = prepare_timeout(u_abs_timeout);
 
 	ret = -EBADF;
@@ -975,6 +990,10 @@ asmlinkage long sys_mq_notify(mqd_t mqdes,
 	struct mqueue_inode_info *info;
 	struct sk_buff *nc;
 
+	ret = audit_mq_notify(mqdes, u_notification);
+	if (ret != 0)
+		return ret;
+
 	nc = NULL;
 	sock = NULL;
 	if (u_notification != NULL) {
@@ -1115,6 +1134,9 @@ asmlinkage long sys_mq_getsetattr(mqd_t mqdes,
 	omqstat = info->attr;
 	omqstat.mq_flags = filp->f_flags & O_NONBLOCK;
 	if (u_mqstat) {
+		ret = audit_mq_getsetattr(mqdes, &mqstat);
+		if (ret != 0)
+			goto out;
 		if (mqstat.mq_flags & O_NONBLOCK)
 			filp->f_flags |= O_NONBLOCK;
 		else

ipc/msg.c

@@ -454,6 +454,11 @@ asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf)
 	err = audit_ipc_obj(ipcp);
 	if (err)
 		goto out_unlock_up;
+	if (cmd==IPC_SET) {
+		err = audit_ipc_set_perm(setbuf.qbytes, setbuf.uid, setbuf.gid, setbuf.mode);
+		if (err)
+			goto out_unlock_up;
+	}
 
 	err = -EPERM;
 	if (current->euid != ipcp->cuid && 
@@ -468,10 +473,6 @@ asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf)
 	switch (cmd) {
 	case IPC_SET:
 	{
-		err = audit_ipc_set_perm(setbuf.qbytes, setbuf.uid, setbuf.gid, setbuf.mode, ipcp);
-		if (err)
-			goto out_unlock_up;
-
 		err = -EPERM;
 		if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE))
 			goto out_unlock_up;

ipc/sem.c

@@ -828,6 +828,11 @@ static int semctl_down(int semid, int semnum, int cmd, int version, union semun
 	if (err)
 		goto out_unlock;
 
+	if (cmd == IPC_SET) {
+		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode);
+		if (err)
+			goto out_unlock;
+	}
 	if (current->euid != ipcp->cuid && 
 	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) {
 	    	err=-EPERM;
@@ -844,9 +849,6 @@ static int semctl_down(int semid, int semnum, int cmd, int version, union semun
 		err = 0;
 		break;
 	case IPC_SET:
-		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode, ipcp);
-		if (err)
-			goto out_unlock;
 		ipcp->uid = setbuf.uid;
 		ipcp->gid = setbuf.gid;
 		ipcp->mode = (ipcp->mode & ~S_IRWXUGO)

ipc/shm.c

@@ -643,7 +643,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 		err = audit_ipc_obj(&(shp->shm_perm));
 		if (err)
 			goto out_unlock_up;
-		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode, &(shp->shm_perm));
+		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode);
 		if (err)
 			goto out_unlock_up;
 		err=-EPERM;

kernel/audit.c

@@ -56,6 +56,7 @@
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/selinux.h>
+#include <linux/inotify.h>
 
 #include "audit.h"
 
@@ -89,6 +90,7 @@ static int	audit_backlog_wait_overflow = 0;
 /* The identity of the user shutting down the audit system. */
 uid_t		audit_sig_uid = -1;
 pid_t		audit_sig_pid = -1;
+u32		audit_sig_sid = 0;
 
 /* Records can be lost in several ways:
    0) [suppressed in audit_alloc]
@@ -102,6 +104,12 @@ static atomic_t    audit_lost = ATOMIC_INIT(0);
 /* The netlink socket. */
 static struct sock *audit_sock;
 
+/* Inotify handle. */
+struct inotify_handle *audit_ih;
+
+/* Hash for inode-based rules */
+struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
+
 /* The audit_freelist is a list of pre-allocated audit buffers (if more
  * than AUDIT_MAXFREE are in use, the audit buffer is freed instead of
  * being placed on the freelist). */
@@ -114,10 +122,8 @@ static struct task_struct *kauditd_task;
 static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
 static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
 
-/* The netlink socket is only to be read by 1 CPU, which lets us assume
- * that list additions and deletions never happen simultaneously in
- * auditsc.c */
-DEFINE_MUTEX(audit_netlink_mutex);
+/* Serialize requests from userspace. */
+static DEFINE_MUTEX(audit_cmd_mutex);
 
 /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
  * audit records.  Since printk uses a 1024 byte buffer, this buffer
@@ -250,7 +256,7 @@ static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid)
 			"audit_rate_limit=%d old=%d by auid=%u",
 			limit, old, loginuid);
 	audit_rate_limit = limit;
-	return old;
+	return 0;
 }
 
 static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid)
@@ -273,7 +279,7 @@ static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid)
 			"audit_backlog_limit=%d old=%d by auid=%u",
 			limit, old, loginuid);
 	audit_backlog_limit = limit;
-	return old;
+	return 0;
 }
 
 static int audit_set_enabled(int state, uid_t loginuid, u32 sid)
@@ -299,7 +305,7 @@ static int audit_set_enabled(int state, uid_t loginuid, u32 sid)
 			"audit_enabled=%d old=%d by auid=%u",
 			state, old, loginuid);
 	audit_enabled = state;
-	return old;
+	return 0;
 }
 
 static int audit_set_failure(int state, uid_t loginuid, u32 sid)
@@ -327,7 +333,7 @@ static int audit_set_failure(int state, uid_t loginuid, u32 sid)
 			"audit_failure=%d old=%d by auid=%u",
 			state, old, loginuid);
 	audit_failure = state;
-	return old;
+	return 0;
 }
 
 static int kauditd_thread(void *dummy)
@@ -363,9 +369,52 @@ static int kauditd_thread(void *dummy)
 			remove_wait_queue(&kauditd_wait, &wait);
 		}
 	}
+}
+
+int audit_send_list(void *_dest)
+{
+	struct audit_netlink_list *dest = _dest;
+	int pid = dest->pid;
+	struct sk_buff *skb;
+
+	/* wait for parent to finish and send an ACK */
+	mutex_lock(&audit_cmd_mutex);
+	mutex_unlock(&audit_cmd_mutex);
+
+	while ((skb = __skb_dequeue(&dest->q)) != NULL)
+		netlink_unicast(audit_sock, skb, pid, 0);
+
+	kfree(dest);
+
 	return 0;
 }
 
+struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
+				 int multi, void *payload, int size)
+{
+	struct sk_buff	*skb;
+	struct nlmsghdr	*nlh;
+	int		len = NLMSG_SPACE(size);
+	void		*data;
+	int		flags = multi ? NLM_F_MULTI : 0;
+	int		t     = done  ? NLMSG_DONE  : type;
+
+	skb = alloc_skb(len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	nlh		 = NLMSG_PUT(skb, pid, seq, t, size);
+	nlh->nlmsg_flags = flags;
+	data		 = NLMSG_DATA(nlh);
+	memcpy(data, payload, size);
+	return skb;
+
+nlmsg_failure:			/* Used by NLMSG_PUT */
+	if (skb)
+		kfree_skb(skb);
+	return NULL;
+}
+
 /**
  * audit_send_reply - send an audit reply message via netlink
  * @pid: process id to send reply to
@@ -383,29 +432,13 @@ void audit_send_reply(int pid, int seq, int type, int done, int multi,
 		      void *payload, int size)
 {
 	struct sk_buff	*skb;
-	struct nlmsghdr	*nlh;
-	int		len = NLMSG_SPACE(size);
-	void		*data;
-	int		flags = multi ? NLM_F_MULTI : 0;
-	int		t     = done  ? NLMSG_DONE  : type;
-
-	skb = alloc_skb(len, GFP_KERNEL);
+	skb = audit_make_reply(pid, seq, type, done, multi, payload, size);
 	if (!skb)
 		return;
-
-	nlh		 = NLMSG_PUT(skb, pid, seq, t, size);
-	nlh->nlmsg_flags = flags;
-	data		 = NLMSG_DATA(nlh);
-	memcpy(data, payload, size);
-
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
 	netlink_unicast(audit_sock, skb, pid, 0);
 	return;
-
-nlmsg_failure:			/* Used by NLMSG_PUT */
-	if (skb)
-		kfree_skb(skb);
 }
 
 /*
@@ -451,7 +484,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct audit_buffer	*ab;
 	u16			msg_type = nlh->nlmsg_type;
 	uid_t			loginuid; /* loginuid of sender */
-	struct audit_sig_info   sig_data;
+	struct audit_sig_info   *sig_data;
+	char			*ctx;
+	u32			len;
 
 	err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type);
 	if (err)
@@ -503,12 +538,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (status_get->mask & AUDIT_STATUS_PID) {
 			int old   = audit_pid;
 			if (sid) {
-				char *ctx = NULL;
-				u32 len;
-				int rc;
-				if ((rc = selinux_ctxid_to_string(
+				if ((err = selinux_ctxid_to_string(
 						sid, &ctx, &len)))
-					return rc;
+					return err;
 				else
 					audit_log(NULL, GFP_KERNEL,
 						AUDIT_CONFIG_CHANGE,
@@ -523,10 +555,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			audit_pid = status_get->pid;
 		}
 		if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
-			audit_set_rate_limit(status_get->rate_limit,
+			err = audit_set_rate_limit(status_get->rate_limit,
 							 loginuid, sid);
 		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
-			audit_set_backlog_limit(status_get->backlog_limit,
+			err = audit_set_backlog_limit(status_get->backlog_limit,
 							loginuid, sid);
 		break;
 	case AUDIT_USER:
@@ -544,8 +576,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 						 "user pid=%d uid=%u auid=%u",
 						 pid, uid, loginuid);
 				if (sid) {
-					char *ctx = NULL;
-					u32 len;
 					if (selinux_ctxid_to_string(
 							sid, &ctx, &len)) {
 						audit_log_format(ab, 
@@ -584,10 +614,21 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					   loginuid, sid);
 		break;
 	case AUDIT_SIGNAL_INFO:
-		sig_data.uid = audit_sig_uid;
-		sig_data.pid = audit_sig_pid;
+		err = selinux_ctxid_to_string(audit_sig_sid, &ctx, &len);
+		if (err)
+			return err;
+		sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
+		if (!sig_data) {
+			kfree(ctx);
+			return -ENOMEM;
+		}
+		sig_data->uid = audit_sig_uid;
+		sig_data->pid = audit_sig_pid;
+		memcpy(sig_data->ctx, ctx, len);
+		kfree(ctx);
 		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO, 
-				0, 0, &sig_data, sizeof(sig_data));
+				0, 0, sig_data, sizeof(*sig_data) + len);
+		kfree(sig_data);
 		break;
 	default:
 		err = -EINVAL;
@@ -629,20 +670,30 @@ static void audit_receive(struct sock *sk, int length)
 	struct sk_buff  *skb;
 	unsigned int qlen;
 
-	mutex_lock(&audit_netlink_mutex);
+	mutex_lock(&audit_cmd_mutex);
 
 	for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) {
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		audit_receive_skb(skb);
 		kfree_skb(skb);
 	}
-	mutex_unlock(&audit_netlink_mutex);
+	mutex_unlock(&audit_cmd_mutex);
 }
 
+#ifdef CONFIG_AUDITSYSCALL
+static const struct inotify_operations audit_inotify_ops = {
+	.handle_event	= audit_handle_ievent,
+	.destroy_watch	= audit_free_parent,
+};
+#endif
 
 /* Initialize audit support at boot time. */
 static int __init audit_init(void)
 {
+#ifdef CONFIG_AUDITSYSCALL
+	int i;
+#endif
+
 	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
 	       audit_default ? "enabled" : "disabled");
 	audit_sock = netlink_kernel_create(NETLINK_AUDIT, 0, audit_receive,
@@ -661,6 +712,16 @@ static int __init audit_init(void)
 	selinux_audit_set_callback(&selinux_audit_rule_update);
 
 	audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
+
+#ifdef CONFIG_AUDITSYSCALL
+	audit_ih = inotify_init(&audit_inotify_ops);
+	if (IS_ERR(audit_ih))
+		audit_panic("cannot initialize inotify handle");
+
+	for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
+		INIT_LIST_HEAD(&audit_inode_hash[i]);
+#endif
+
 	return 0;
 }
 __initcall(audit_init);
@@ -690,10 +751,12 @@ static void audit_buffer_free(struct audit_buffer *ab)
 		kfree_skb(ab->skb);
 
 	spin_lock_irqsave(&audit_freelist_lock, flags);
-	if (++audit_freelist_count > AUDIT_MAXFREE)
+	if (audit_freelist_count > AUDIT_MAXFREE)
 		kfree(ab);
-	else
+	else {
+		audit_freelist_count++;
 		list_add(&ab->list, &audit_freelist);
+	}
 	spin_unlock_irqrestore(&audit_freelist_lock, flags);
 }
 
@@ -988,28 +1051,76 @@ void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf,
 	skb_put(skb, len << 1); /* new string is twice the old string */
 }
 
+/*
+ * Format a string of no more than slen characters into the audit buffer,
+ * enclosed in quote marks.
+ */
+static void audit_log_n_string(struct audit_buffer *ab, size_t slen,
+			       const char *string)
+{
+	int avail, new_len;
+	unsigned char *ptr;
+	struct sk_buff *skb;
+
+	BUG_ON(!ab->skb);
+	skb = ab->skb;
+	avail = skb_tailroom(skb);
+	new_len = slen + 3;	/* enclosing quotes + null terminator */
+	if (new_len > avail) {
+		avail = audit_expand(ab, new_len);
+		if (!avail)
+			return;
+	}
+	ptr = skb->tail;
+	*ptr++ = '"';
+	memcpy(ptr, string, slen);
+	ptr += slen;
+	*ptr++ = '"';
+	*ptr = 0;
+	skb_put(skb, slen + 2);	/* don't include null terminator */
+}
+
 /**
- * audit_log_unstrustedstring - log a string that may contain random characters
+ * audit_log_n_unstrustedstring - log a string that may contain random characters
  * @ab: audit_buffer
+ * @len: lenth of string (not including trailing null)
  * @string: string to be logged
  *
  * This code will escape a string that is passed to it if the string
  * contains a control character, unprintable character, double quote mark,
  * or a space. Unescaped strings will start and end with a double quote mark.
  * Strings that are escaped are printed in hex (2 digits per char).
+ *
+ * The caller specifies the number of characters in the string to log, which may
+ * or may not be the entire string.
  */
-void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
+const char *audit_log_n_untrustedstring(struct audit_buffer *ab, size_t len,
+					const char *string)
 {
 	const unsigned char *p = string;
 
 	while (*p) {
 		if (*p == '"' || *p < 0x21 || *p > 0x7f) {
-			audit_log_hex(ab, string, strlen(string));
-			return;
+			audit_log_hex(ab, string, len);
+			return string + len + 1;
 		}
 		p++;
 	}
-	audit_log_format(ab, "\"%s\"", string);
+	audit_log_n_string(ab, len, string);
+	return p + 1;
+}
+
+/**
+ * audit_log_unstrustedstring - log a string that may contain random characters
+ * @ab: audit_buffer
+ * @string: string to be logged
+ *
+ * Same as audit_log_n_unstrustedstring(), except that strlen is used to
+ * determine string length.
+ */
+const char *audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
+{
+	return audit_log_n_untrustedstring(ab, strlen(string), string);
 }
 
 /* This is a helper-function to print the escaped d_path */

kernel/audit.h

@@ -19,9 +19,9 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-#include <linux/mutex.h>
 #include <linux/fs.h>
 #include <linux/audit.h>
+#include <linux/skbuff.h>
 
 /* 0 = no checking
    1 = put_count checking
@@ -53,6 +53,18 @@ enum audit_state {
 };
 
 /* Rule lists */
+struct audit_parent;
+
+struct audit_watch {
+	atomic_t		count;	/* reference count */
+	char			*path;	/* insertion path */
+	dev_t			dev;	/* associated superblock device */
+	unsigned long		ino;	/* associated inode number */
+	struct audit_parent	*parent; /* associated parent */
+	struct list_head	wlist;	/* entry in parent->watches list */
+	struct list_head	rules;	/* associated rules */
+};
+
 struct audit_field {
 	u32				type;
 	u32				val;
@@ -70,6 +82,9 @@ struct audit_krule {
 	u32			buflen; /* for data alloc on list rules */
 	u32			field_count;
 	struct audit_field	*fields;
+	struct audit_field	*inode_f; /* quick access to an inode field */
+	struct audit_watch	*watch;	/* associated watch */
+	struct list_head	rlist;	/* entry in audit_watch.rules list */
 };
 
 struct audit_entry {
@@ -78,15 +93,53 @@ struct audit_entry {
 	struct audit_krule	rule;
 };
 
-
 extern int audit_pid;
-extern int audit_comparator(const u32 left, const u32 op, const u32 right);
 
+#define AUDIT_INODE_BUCKETS	32
+extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
+
+static inline int audit_hash_ino(u32 ino)
+{
+	return (ino & (AUDIT_INODE_BUCKETS-1));
+}
+
+extern int audit_comparator(const u32 left, const u32 op, const u32 right);
+extern int audit_compare_dname_path(const char *dname, const char *path,
+				    int *dirlen);
+extern struct sk_buff *	    audit_make_reply(int pid, int seq, int type,
+					     int done, int multi,
+					     void *payload, int size);
 extern void		    audit_send_reply(int pid, int seq, int type,
 					     int done, int multi,
 					     void *payload, int size);
 extern void		    audit_log_lost(const char *message);
 extern void		    audit_panic(const char *message);
-extern struct mutex audit_netlink_mutex;
 
+struct audit_netlink_list {
+	int pid;
+	struct sk_buff_head q;
+};
+
+int audit_send_list(void *);
+
+struct inotify_watch;
+extern void audit_free_parent(struct inotify_watch *);
+extern void audit_handle_ievent(struct inotify_watch *, u32, u32, u32,
+				const char *, struct inode *);
 extern int selinux_audit_rule_update(void);
+
+#ifdef CONFIG_AUDITSYSCALL
+extern void __audit_signal_info(int sig, struct task_struct *t);
+static inline void audit_signal_info(int sig, struct task_struct *t)
+{
+	if (unlikely(audit_pid && t->tgid == audit_pid))
+		__audit_signal_info(sig, t);
+}
+extern enum audit_state audit_filter_inodes(struct task_struct *,
+					    struct audit_context *);
+extern void audit_set_auditable(struct audit_context *);
+#else
+#define audit_signal_info(s,t)
+#define audit_filter_inodes(t,c) AUDIT_DISABLED
+#define audit_set_auditable(c)
+#endif

kernel/auditsc.c

@@ -3,7 +3,7 @@
  *
  * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
  * Copyright 2005 Hewlett-Packard Development Company, L.P.
- * Copyright (C) 2005 IBM Corporation
+ * Copyright (C) 2005, 2006 IBM Corporation
  * All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -29,6 +29,9 @@
  * this file -- see entry.S) is based on a GPL'd patch written by
  * okir@suse.de and Copyright 2003 SuSE Linux AG.
  *
+ * POSIX message queue support added by George Wilson <ltcgcw@us.ibm.com>,
+ * 2006.
+ *
  * The support of additional filter rules compares (>, <, >=, <=) was
  * added by Dustin Kirkland <dustin.kirkland@us.ibm.com>, 2005.
  *
@@ -49,6 +52,7 @@
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/socket.h>
+#include <linux/mqueue.h>
 #include <linux/audit.h>
 #include <linux/personality.h>
 #include <linux/time.h>
@@ -59,6 +63,8 @@
 #include <linux/list.h>
 #include <linux/tty.h>
 #include <linux/selinux.h>
+#include <linux/binfmts.h>
+#include <linux/syscalls.h>
 
 #include "audit.h"
 
@@ -76,6 +82,9 @@ extern int audit_enabled;
  * path_lookup. */
 #define AUDIT_NAMES_RESERVED 7
 
+/* Indicates that audit should log the full pathname. */
+#define AUDIT_NAME_FULL -1
+
 /* When fs/namei.c:getname() is called, we store the pointer in name and
  * we don't let putname() free it (instead we free all of the saved
  * pointers at syscall exit time).
@@ -83,8 +92,9 @@ extern int audit_enabled;
  * Further, in fs/namei.c:path_lookup() we store the inode and device. */
 struct audit_names {
 	const char	*name;
+	int		name_len;	/* number of name's characters to log */
+	unsigned	name_put;	/* call __putname() for this name */
 	unsigned long	ino;
-	unsigned long	pino;
 	dev_t		dev;
 	umode_t		mode;
 	uid_t		uid;
@@ -100,6 +110,33 @@ struct audit_aux_data {
 
 #define AUDIT_AUX_IPCPERM	0
 
+struct audit_aux_data_mq_open {
+	struct audit_aux_data	d;
+	int			oflag;
+	mode_t			mode;
+	struct mq_attr		attr;
+};
+
+struct audit_aux_data_mq_sendrecv {
+	struct audit_aux_data	d;
+	mqd_t			mqdes;
+	size_t			msg_len;
+	unsigned int		msg_prio;
+	struct timespec		abs_timeout;
+};
+
+struct audit_aux_data_mq_notify {
+	struct audit_aux_data	d;
+	mqd_t			mqdes;
+	struct sigevent 	notification;
+};
+
+struct audit_aux_data_mq_getsetattr {
+	struct audit_aux_data	d;
+	mqd_t			mqdes;
+	struct mq_attr 		mqstat;
+};
+
 struct audit_aux_data_ipcctl {
 	struct audit_aux_data	d;
 	struct ipc_perm		p;
@@ -110,6 +147,13 @@ struct audit_aux_data_ipcctl {
 	u32			osid;
 };
 
+struct audit_aux_data_execve {
+	struct audit_aux_data	d;
+	int argc;
+	int envc;
+	char mem[0];
+};
+
 struct audit_aux_data_socketcall {
 	struct audit_aux_data	d;
 	int			nargs;
@@ -148,7 +192,7 @@ struct audit_context {
 	struct audit_aux_data *aux;
 
 				/* Save things to print about task_struct */
-	pid_t		    pid;
+	pid_t		    pid, ppid;
 	uid_t		    uid, euid, suid, fsuid;
 	gid_t		    gid, egid, sgid, fsgid;
 	unsigned long	    personality;
@@ -160,12 +204,13 @@ struct audit_context {
 #endif
 };
 
-
+/* Determine if any context name data matches a rule's watch data */
 /* Compare a task_struct with an audit_rule.  Return 1 on match, 0
  * otherwise. */
 static int audit_filter_rules(struct task_struct *tsk,
 			      struct audit_krule *rule,
 			      struct audit_context *ctx,
+			      struct audit_names *name,
 			      enum audit_state *state)
 {
 	int i, j, need_sid = 1;
@@ -179,6 +224,10 @@ static int audit_filter_rules(struct task_struct *tsk,
 		case AUDIT_PID:
 			result = audit_comparator(tsk->pid, f->op, f->val);
 			break;
+		case AUDIT_PPID:
+			if (ctx)
+				result = audit_comparator(ctx->ppid, f->op, f->val);
+			break;
 		case AUDIT_UID:
 			result = audit_comparator(tsk->uid, f->op, f->val);
 			break;
@@ -224,7 +273,10 @@ static int audit_filter_rules(struct task_struct *tsk,
 			}
 			break;
 		case AUDIT_DEVMAJOR:
-			if (ctx) {
+			if (name)
+				result = audit_comparator(MAJOR(name->dev),
+							  f->op, f->val);
+			else if (ctx) {
 				for (j = 0; j < ctx->name_count; j++) {
 					if (audit_comparator(MAJOR(ctx->names[j].dev),	f->op, f->val)) {
 						++result;
@@ -234,7 +286,10 @@ static int audit_filter_rules(struct task_struct *tsk,
 			}
 			break;
 		case AUDIT_DEVMINOR:
-			if (ctx) {
+			if (name)
+				result = audit_comparator(MINOR(name->dev),
+							  f->op, f->val);
+			else if (ctx) {
 				for (j = 0; j < ctx->name_count; j++) {
 					if (audit_comparator(MINOR(ctx->names[j].dev), f->op, f->val)) {
 						++result;
@@ -244,16 +299,22 @@ static int audit_filter_rules(struct task_struct *tsk,
 			}
 			break;
 		case AUDIT_INODE:
-			if (ctx) {
+			if (name)
+				result = (name->ino == f->val);
+			else if (ctx) {
 				for (j = 0; j < ctx->name_count; j++) {
-					if (audit_comparator(ctx->names[j].ino, f->op, f->val) ||
-					    audit_comparator(ctx->names[j].pino, f->op, f->val)) {
+					if (audit_comparator(ctx->names[j].ino, f->op, f->val)) {
 						++result;
 						break;
 					}
 				}
 			}
 			break;
+		case AUDIT_WATCH:
+			if (name && rule->watch->ino != (unsigned long)-1)
+				result = (name->dev == rule->watch->dev &&
+					  name->ino == rule->watch->ino);
+			break;
 		case AUDIT_LOGINUID:
 			result = 0;
 			if (ctx)
@@ -294,7 +355,6 @@ static int audit_filter_rules(struct task_struct *tsk,
 	}
 	switch (rule->action) {
 	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
-	case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT;  break;
 	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
 	}
 	return 1;
@@ -311,7 +371,7 @@ static enum audit_state audit_filter_task(struct task_struct *tsk)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
-		if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
+		if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state)) {
 			rcu_read_unlock();
 			return state;
 		}
@@ -341,8 +401,47 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 		int bit  = AUDIT_BIT(ctx->major);
 
 		list_for_each_entry_rcu(e, list, list) {
-			if ((e->rule.mask[word] & bit) == bit
-					&& audit_filter_rules(tsk, &e->rule, ctx, &state)) {
+			if ((e->rule.mask[word] & bit) == bit &&
+			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
+					       &state)) {
+				rcu_read_unlock();
+				return state;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return AUDIT_BUILD_CONTEXT;
+}
+
+/* At syscall exit time, this filter is called if any audit_names[] have been
+ * collected during syscall processing.  We only check rules in sublists at hash
+ * buckets applicable to the inode numbers in audit_names[].
+ * Regarding audit_state, same rules apply as for audit_filter_syscall().
+ */
+enum audit_state audit_filter_inodes(struct task_struct *tsk,
+				     struct audit_context *ctx)
+{
+	int i;
+	struct audit_entry *e;
+	enum audit_state state;
+
+	if (audit_pid && tsk->tgid == audit_pid)
+		return AUDIT_DISABLED;
+
+	rcu_read_lock();
+	for (i = 0; i < ctx->name_count; i++) {
+		int word = AUDIT_WORD(ctx->major);
+		int bit  = AUDIT_BIT(ctx->major);
+		struct audit_names *n = &ctx->names[i];
+		int h = audit_hash_ino((u32)n->ino);
+		struct list_head *list = &audit_inode_hash[h];
+
+		if (list_empty(list))
+			continue;
+
+		list_for_each_entry_rcu(e, list, list) {
+			if ((e->rule.mask[word] & bit) == bit &&
+			    audit_filter_rules(tsk, &e->rule, ctx, n, &state)) {
 				rcu_read_unlock();
 				return state;
 			}
@@ -352,6 +451,11 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 	return AUDIT_BUILD_CONTEXT;
 }
 
+void audit_set_auditable(struct audit_context *ctx)
+{
+	ctx->auditable = 1;
+}
+
 static inline struct audit_context *audit_get_context(struct task_struct *tsk,
 						      int return_valid,
 						      int return_code)
@@ -365,12 +469,22 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
 
 	if (context->in_syscall && !context->auditable) {
 		enum audit_state state;
+
 		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
+		if (state == AUDIT_RECORD_CONTEXT) {
+			context->auditable = 1;
+			goto get_context;
+		}
+
+		state = audit_filter_inodes(tsk, context);
 		if (state == AUDIT_RECORD_CONTEXT)
 			context->auditable = 1;
+
 	}
 
+get_context:
 	context->pid = tsk->pid;
+	context->ppid = sys_getppid();	/* sic.  tsk == current in all cases */
 	context->uid = tsk->uid;
 	context->gid = tsk->gid;
 	context->euid = tsk->euid;
@@ -413,7 +527,7 @@ static inline void audit_free_names(struct audit_context *context)
 #endif
 
 	for (i = 0; i < context->name_count; i++) {
-		if (context->names[i].name)
+		if (context->names[i].name && context->names[i].name_put)
 			__putname(context->names[i].name);
 	}
 	context->name_count = 0;
@@ -606,7 +720,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		tty = "(none)";
 	audit_log_format(ab,
 		  " a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
-		  " pid=%d auid=%u uid=%u gid=%u"
+		  " ppid=%d pid=%d auid=%u uid=%u gid=%u"
 		  " euid=%u suid=%u fsuid=%u"
 		  " egid=%u sgid=%u fsgid=%u tty=%s",
 		  context->argv[0],
@@ -614,6 +728,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		  context->argv[2],
 		  context->argv[3],
 		  context->name_count,
+		  context->ppid,
 		  context->pid,
 		  context->loginuid,
 		  context->uid,
@@ -630,11 +745,48 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			continue; /* audit_panic has been called */
 
 		switch (aux->type) {
+		case AUDIT_MQ_OPEN: {
+			struct audit_aux_data_mq_open *axi = (void *)aux;
+			audit_log_format(ab,
+				"oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld "
+				"mq_msgsize=%ld mq_curmsgs=%ld",
+				axi->oflag, axi->mode, axi->attr.mq_flags,
+				axi->attr.mq_maxmsg, axi->attr.mq_msgsize,
+				axi->attr.mq_curmsgs);
+			break; }
+
+		case AUDIT_MQ_SENDRECV: {
+			struct audit_aux_data_mq_sendrecv *axi = (void *)aux;
+			audit_log_format(ab,
+				"mqdes=%d msg_len=%zd msg_prio=%u "
+				"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
+				axi->mqdes, axi->msg_len, axi->msg_prio,
+				axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec);
+			break; }
+
+		case AUDIT_MQ_NOTIFY: {
+			struct audit_aux_data_mq_notify *axi = (void *)aux;
+			audit_log_format(ab,
+				"mqdes=%d sigev_signo=%d",
+				axi->mqdes,
+				axi->notification.sigev_signo);
+			break; }
+
+		case AUDIT_MQ_GETSETATTR: {
+			struct audit_aux_data_mq_getsetattr *axi = (void *)aux;
+			audit_log_format(ab,
+				"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
+				"mq_curmsgs=%ld ",
+				axi->mqdes,
+				axi->mqstat.mq_flags, axi->mqstat.mq_maxmsg,
+				axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs);
+			break; }
+
 		case AUDIT_IPC: {
 			struct audit_aux_data_ipcctl *axi = (void *)aux;
 			audit_log_format(ab, 
-				 " qbytes=%lx iuid=%u igid=%u mode=%x",
-				 axi->qbytes, axi->uid, axi->gid, axi->mode);
+				 "ouid=%u ogid=%u mode=%x",
+				 axi->uid, axi->gid, axi->mode);
 			if (axi->osid != 0) {
 				char *ctx = NULL;
 				u32 len;
@@ -652,19 +804,18 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		case AUDIT_IPC_SET_PERM: {
 			struct audit_aux_data_ipcctl *axi = (void *)aux;
 			audit_log_format(ab,
-				" new qbytes=%lx new iuid=%u new igid=%u new mode=%x",
+				"qbytes=%lx ouid=%u ogid=%u mode=%x",
 				axi->qbytes, axi->uid, axi->gid, axi->mode);
-			if (axi->osid != 0) {
-				char *ctx = NULL;
-				u32 len;
-				if (selinux_ctxid_to_string(
-						axi->osid, &ctx, &len)) {
-					audit_log_format(ab, " osid=%u",
-							axi->osid);
-					call_panic = 1;
-				} else
-					audit_log_format(ab, " obj=%s", ctx);
-				kfree(ctx);
+			break; }
+
+		case AUDIT_EXECVE: {
+			struct audit_aux_data_execve *axi = (void *)aux;
+			int i;
+			const char *p;
+			for (i = 0, p = axi->mem; i < axi->argc; i++) {
+				audit_log_format(ab, "a%d=", i);
+				p = audit_log_untrustedstring(ab, p);
+				audit_log_format(ab, "\n");
 			}
 			break; }
 
@@ -700,8 +851,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		}
 	}
 	for (i = 0; i < context->name_count; i++) {
-		unsigned long ino  = context->names[i].ino;
-		unsigned long pino = context->names[i].pino;
+		struct audit_names *n = &context->names[i];
 
 		ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
 		if (!ab)
@@ -709,33 +859,47 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 
 		audit_log_format(ab, "item=%d", i);
 
-		audit_log_format(ab, " name=");
-		if (context->names[i].name)
-			audit_log_untrustedstring(ab, context->names[i].name);
-		else
-			audit_log_format(ab, "(null)");
-
-		if (pino != (unsigned long)-1)
-			audit_log_format(ab, " parent=%lu",  pino);
-		if (ino != (unsigned long)-1)
-			audit_log_format(ab, " inode=%lu",  ino);
-		if ((pino != (unsigned long)-1) || (ino != (unsigned long)-1))
-			audit_log_format(ab, " dev=%02x:%02x mode=%#o" 
-					 " ouid=%u ogid=%u rdev=%02x:%02x", 
-					 MAJOR(context->names[i].dev), 
-					 MINOR(context->names[i].dev), 
-					 context->names[i].mode, 
-					 context->names[i].uid, 
-					 context->names[i].gid, 
-					 MAJOR(context->names[i].rdev), 
-					 MINOR(context->names[i].rdev));
-		if (context->names[i].osid != 0) {
+		if (n->name) {
+			switch(n->name_len) {
+			case AUDIT_NAME_FULL:
+				/* log the full path */
+				audit_log_format(ab, " name=");
+				audit_log_untrustedstring(ab, n->name);
+				break;
+			case 0:
+				/* name was specified as a relative path and the
+				 * directory component is the cwd */
+				audit_log_d_path(ab, " name=", context->pwd,
+						 context->pwdmnt);
+				break;
+			default:
+				/* log the name's directory component */
+				audit_log_format(ab, " name=");
+				audit_log_n_untrustedstring(ab, n->name_len,
+							    n->name);
+			}
+		} else
+			audit_log_format(ab, " name=(null)");
+
+		if (n->ino != (unsigned long)-1) {
+			audit_log_format(ab, " inode=%lu"
+					 " dev=%02x:%02x mode=%#o"
+					 " ouid=%u ogid=%u rdev=%02x:%02x",
+					 n->ino,
+					 MAJOR(n->dev),
+					 MINOR(n->dev),
+					 n->mode,
+					 n->uid,
+					 n->gid,
+					 MAJOR(n->rdev),
+					 MINOR(n->rdev));
+		}
+		if (n->osid != 0) {
 			char *ctx = NULL;
 			u32 len;
 			if (selinux_ctxid_to_string(
-				context->names[i].osid, &ctx, &len)) {
-				audit_log_format(ab, " osid=%u",
-						context->names[i].osid);
+				n->osid, &ctx, &len)) {
+				audit_log_format(ab, " osid=%u", n->osid);
 				call_panic = 2;
 			} else
 				audit_log_format(ab, " obj=%s", ctx);
@@ -908,11 +1072,11 @@ void audit_syscall_exit(int valid, long return_code)
  * Add a name to the list of audit names for this context.
  * Called from fs/namei.c:getname().
  */
-void audit_getname(const char *name)
+void __audit_getname(const char *name)
 {
 	struct audit_context *context = current->audit_context;
 
-	if (!context || IS_ERR(name) || !name)
+	if (IS_ERR(name) || !name)
 		return;
 
 	if (!context->in_syscall) {
@@ -925,6 +1089,8 @@ void audit_getname(const char *name)
 	}
 	BUG_ON(context->name_count >= AUDIT_NAMES);
 	context->names[context->name_count].name = name;
+	context->names[context->name_count].name_len = AUDIT_NAME_FULL;
+	context->names[context->name_count].name_put = 1;
 	context->names[context->name_count].ino  = (unsigned long)-1;
 	++context->name_count;
 	if (!context->pwd) {
@@ -991,11 +1157,10 @@ static void audit_inode_context(int idx, const struct inode *inode)
  * audit_inode - store the inode and device from a lookup
  * @name: name being audited
  * @inode: inode being audited
- * @flags: lookup flags (as used in path_lookup())
  *
  * Called from fs/namei.c:path_lookup().
  */
-void __audit_inode(const char *name, const struct inode *inode, unsigned flags)
+void __audit_inode(const char *name, const struct inode *inode)
 {
 	int idx;
 	struct audit_context *context = current->audit_context;
@@ -1021,20 +1186,13 @@ void __audit_inode(const char *name, const struct inode *inode, unsigned flags)
 		++context->ino_count;
 #endif
 	}
+	context->names[idx].ino   = inode->i_ino;
 	context->names[idx].dev	  = inode->i_sb->s_dev;
 	context->names[idx].mode  = inode->i_mode;
 	context->names[idx].uid   = inode->i_uid;
 	context->names[idx].gid   = inode->i_gid;
 	context->names[idx].rdev  = inode->i_rdev;
 	audit_inode_context(idx, inode);
-	if ((flags & LOOKUP_PARENT) && (strcmp(name, "/") != 0) && 
-	    (strcmp(name, ".") != 0)) {
-		context->names[idx].ino   = (unsigned long)-1;
-		context->names[idx].pino  = inode->i_ino;
-	} else {
-		context->names[idx].ino   = inode->i_ino;
-		context->names[idx].pino  = (unsigned long)-1;
-	}
 }
 
 /**
@@ -1056,51 +1214,40 @@ void __audit_inode_child(const char *dname, const struct inode *inode,
 {
 	int idx;
 	struct audit_context *context = current->audit_context;
+	const char *found_name = NULL;
+	int dirlen = 0;
 
 	if (!context->in_syscall)
 		return;
 
 	/* determine matching parent */
-	if (dname)
-		for (idx = 0; idx < context->name_count; idx++)
-			if (context->names[idx].pino == pino) {
-				const char *n;
-				const char *name = context->names[idx].name;
-				int dlen = strlen(dname);
-				int nlen = name ? strlen(name) : 0;
-
-				if (nlen < dlen)
-					continue;
-				
-				/* disregard trailing slashes */
-				n = name + nlen - 1;
-				while ((*n == '/') && (n > name))
-					n--;
-
-				/* find last path component */
-				n = n - dlen + 1;
-				if (n < name)
-					continue;
-				else if (n > name) {
-					if (*--n != '/')
-						continue;
-					else
-						n++;
-				}
-
-				if (strncmp(n, dname, dlen) == 0)
-					goto update_context;
+	if (!dname)
+		goto update_context;
+	for (idx = 0; idx < context->name_count; idx++)
+		if (context->names[idx].ino == pino) {
+			const char *name = context->names[idx].name;
+
+			if (!name)
+				continue;
+
+			if (audit_compare_dname_path(dname, name, &dirlen) == 0) {
+				context->names[idx].name_len = dirlen;
+				found_name = name;
+				break;
 			}
+		}
 
-	/* catch-all in case match not found */
+update_context:
 	idx = context->name_count++;
-	context->names[idx].name  = NULL;
-	context->names[idx].pino  = pino;
 #if AUDIT_DEBUG
 	context->ino_count++;
 #endif
+	/* Re-use the name belonging to the slot for a matching parent directory.
+	 * All names for this context are relinquished in audit_free_names() */
+	context->names[idx].name = found_name;
+	context->names[idx].name_len = AUDIT_NAME_FULL;
+	context->names[idx].name_put = 0;	/* don't call __putname() */
 
-update_context:
 	if (inode) {
 		context->names[idx].ino   = inode->i_ino;
 		context->names[idx].dev	  = inode->i_sb->s_dev;
@@ -1109,7 +1256,8 @@ update_context:
 		context->names[idx].gid   = inode->i_gid;
 		context->names[idx].rdev  = inode->i_rdev;
 		audit_inode_context(idx, inode);
-	}
+	} else
+		context->names[idx].ino   = (unsigned long)-1;
 }
 
 /**
@@ -1142,18 +1290,23 @@ void auditsc_get_stamp(struct audit_context *ctx,
  */
 int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
 {
-	if (task->audit_context) {
-		struct audit_buffer *ab;
-
-		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
-		if (ab) {
-			audit_log_format(ab, "login pid=%d uid=%u "
-				"old auid=%u new auid=%u",
-				task->pid, task->uid, 
-				task->audit_context->loginuid, loginuid);
-			audit_log_end(ab);
+	struct audit_context *context = task->audit_context;
+
+	if (context) {
+		/* Only log if audit is enabled */
+		if (context->in_syscall) {
+			struct audit_buffer *ab;
+
+			ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+			if (ab) {
+				audit_log_format(ab, "login pid=%d uid=%u "
+					"old auid=%u new auid=%u",
+					task->pid, task->uid,
+					context->loginuid, loginuid);
+				audit_log_end(ab);
+			}
 		}
-		task->audit_context->loginuid = loginuid;
+		context->loginuid = loginuid;
 	}
 	return 0;
 }
@@ -1170,19 +1323,220 @@ uid_t audit_get_loginuid(struct audit_context *ctx)
 }
 
 /**
- * audit_ipc_obj - record audit data for ipc object
- * @ipcp: ipc permissions
+ * __audit_mq_open - record audit data for a POSIX MQ open
+ * @oflag: open flag
+ * @mode: mode bits
+ * @u_attr: queue attributes
  *
  * Returns 0 for success or NULL context or < 0 on error.
  */
-int audit_ipc_obj(struct kern_ipc_perm *ipcp)
+int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
 {
-	struct audit_aux_data_ipcctl *ax;
+	struct audit_aux_data_mq_open *ax;
+	struct audit_context *context = current->audit_context;
+
+	if (!audit_enabled)
+		return 0;
+
+	if (likely(!context))
+		return 0;
+
+	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
+	if (!ax)
+		return -ENOMEM;
+
+	if (u_attr != NULL) {
+		if (copy_from_user(&ax->attr, u_attr, sizeof(ax->attr))) {
+			kfree(ax);
+			return -EFAULT;
+		}
+	} else
+		memset(&ax->attr, 0, sizeof(ax->attr));
+
+	ax->oflag = oflag;
+	ax->mode = mode;
+
+	ax->d.type = AUDIT_MQ_OPEN;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+/**
+ * __audit_mq_timedsend - record audit data for a POSIX MQ timed send
+ * @mqdes: MQ descriptor
+ * @msg_len: Message length
+ * @msg_prio: Message priority
+ * @abs_timeout: Message timeout in absolute time
+ *
+ * Returns 0 for success or NULL context or < 0 on error.
+ */
+int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
+			const struct timespec __user *u_abs_timeout)
+{
+	struct audit_aux_data_mq_sendrecv *ax;
+	struct audit_context *context = current->audit_context;
+
+	if (!audit_enabled)
+		return 0;
+
+	if (likely(!context))
+		return 0;
+
+	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
+	if (!ax)
+		return -ENOMEM;
+
+	if (u_abs_timeout != NULL) {
+		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
+			kfree(ax);
+			return -EFAULT;
+		}
+	} else
+		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
+
+	ax->mqdes = mqdes;
+	ax->msg_len = msg_len;
+	ax->msg_prio = msg_prio;
+
+	ax->d.type = AUDIT_MQ_SENDRECV;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+/**
+ * __audit_mq_timedreceive - record audit data for a POSIX MQ timed receive
+ * @mqdes: MQ descriptor
+ * @msg_len: Message length
+ * @msg_prio: Message priority
+ * @abs_timeout: Message timeout in absolute time
+ *
+ * Returns 0 for success or NULL context or < 0 on error.
+ */
+int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len,
+				unsigned int __user *u_msg_prio,
+				const struct timespec __user *u_abs_timeout)
+{
+	struct audit_aux_data_mq_sendrecv *ax;
+	struct audit_context *context = current->audit_context;
+
+	if (!audit_enabled)
+		return 0;
+
+	if (likely(!context))
+		return 0;
+
+	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
+	if (!ax)
+		return -ENOMEM;
+
+	if (u_msg_prio != NULL) {
+		if (get_user(ax->msg_prio, u_msg_prio)) {
+			kfree(ax);
+			return -EFAULT;
+		}
+	} else
+		ax->msg_prio = 0;
+
+	if (u_abs_timeout != NULL) {
+		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
+			kfree(ax);
+			return -EFAULT;
+		}
+	} else
+		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
+
+	ax->mqdes = mqdes;
+	ax->msg_len = msg_len;
+
+	ax->d.type = AUDIT_MQ_SENDRECV;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+/**
+ * __audit_mq_notify - record audit data for a POSIX MQ notify
+ * @mqdes: MQ descriptor
+ * @u_notification: Notification event
+ *
+ * Returns 0 for success or NULL context or < 0 on error.
+ */
+
+int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
+{
+	struct audit_aux_data_mq_notify *ax;
+	struct audit_context *context = current->audit_context;
+
+	if (!audit_enabled)
+		return 0;
+
+	if (likely(!context))
+		return 0;
+
+	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
+	if (!ax)
+		return -ENOMEM;
+
+	if (u_notification != NULL) {
+		if (copy_from_user(&ax->notification, u_notification, sizeof(ax->notification))) {
+			kfree(ax);
+			return -EFAULT;
+		}
+	} else
+		memset(&ax->notification, 0, sizeof(ax->notification));
+
+	ax->mqdes = mqdes;
+
+	ax->d.type = AUDIT_MQ_NOTIFY;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+/**
+ * __audit_mq_getsetattr - record audit data for a POSIX MQ get/set attribute
+ * @mqdes: MQ descriptor
+ * @mqstat: MQ flags
+ *
+ * Returns 0 for success or NULL context or < 0 on error.
+ */
+int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
+{
+	struct audit_aux_data_mq_getsetattr *ax;
 	struct audit_context *context = current->audit_context;
 
+	if (!audit_enabled)
+		return 0;
+
 	if (likely(!context))
 		return 0;
 
+	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
+	if (!ax)
+		return -ENOMEM;
+
+	ax->mqdes = mqdes;
+	ax->mqstat = *mqstat;
+
+	ax->d.type = AUDIT_MQ_GETSETATTR;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+/**
+ * audit_ipc_obj - record audit data for ipc object
+ * @ipcp: ipc permissions
+ *
+ * Returns 0 for success or NULL context or < 0 on error.
+ */
+int __audit_ipc_obj(struct kern_ipc_perm *ipcp)
+{
+	struct audit_aux_data_ipcctl *ax;
+	struct audit_context *context = current->audit_context;
+
 	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
 	if (!ax)
 		return -ENOMEM;
@@ -1207,14 +1561,11 @@ int audit_ipc_obj(struct kern_ipc_perm *ipcp)
  *
  * Returns 0 for success or NULL context or < 0 on error.
  */
-int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode, struct kern_ipc_perm *ipcp)
+int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
 {
 	struct audit_aux_data_ipcctl *ax;
 	struct audit_context *context = current->audit_context;
 
-	if (likely(!context))
-		return 0;
-
 	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
 	if (!ax)
 		return -ENOMEM;
@@ -1223,7 +1574,6 @@ int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode,
 	ax->uid = uid;
 	ax->gid = gid;
 	ax->mode = mode;
-	selinux_get_ipc_sid(ipcp, &ax->osid);
 
 	ax->d.type = AUDIT_IPC_SET_PERM;
 	ax->d.next = context->aux;
@@ -1231,6 +1581,39 @@ int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode,
 	return 0;
 }
 
+int audit_bprm(struct linux_binprm *bprm)
+{
+	struct audit_aux_data_execve *ax;
+	struct audit_context *context = current->audit_context;
+	unsigned long p, next;
+	void *to;
+
+	if (likely(!audit_enabled || !context))
+		return 0;
+
+	ax = kmalloc(sizeof(*ax) + PAGE_SIZE * MAX_ARG_PAGES - bprm->p,
+				GFP_KERNEL);
+	if (!ax)
+		return -ENOMEM;
+
+	ax->argc = bprm->argc;
+	ax->envc = bprm->envc;
+	for (p = bprm->p, to = ax->mem; p < MAX_ARG_PAGES*PAGE_SIZE; p = next) {
+		struct page *page = bprm->page[p / PAGE_SIZE];
+		void *kaddr = kmap(page);
+		next = (p + PAGE_SIZE) & ~(PAGE_SIZE - 1);
+		memcpy(to, kaddr + (p & (PAGE_SIZE - 1)), next - p);
+		to += next - p;
+		kunmap(page);
+	}
+
+	ax->d.type = AUDIT_EXECVE;
+	ax->d.next = context->aux;
+	context->aux = (void *)ax;
+	return 0;
+}
+
+
 /**
  * audit_socketcall - record audit data for sys_socketcall
  * @nargs: number of args
@@ -1325,19 +1708,20 @@ int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt)
  * If the audit subsystem is being terminated, record the task (pid)
  * and uid that is doing that.
  */
-void audit_signal_info(int sig, struct task_struct *t)
+void __audit_signal_info(int sig, struct task_struct *t)
 {
 	extern pid_t audit_sig_pid;
 	extern uid_t audit_sig_uid;
-
-	if (unlikely(audit_pid && t->tgid == audit_pid)) {
-		if (sig == SIGTERM || sig == SIGHUP) {
-			struct audit_context *ctx = current->audit_context;
-			audit_sig_pid = current->pid;
-			if (ctx)
-				audit_sig_uid = ctx->loginuid;
-			else
-				audit_sig_uid = current->uid;
-		}
+	extern u32 audit_sig_sid;
+
+	if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) {
+		struct task_struct *tsk = current;
+		struct audit_context *ctx = tsk->audit_context;
+		audit_sig_pid = tsk->pid;
+		if (ctx)
+			audit_sig_uid = ctx->loginuid;
+		else
+			audit_sig_uid = tsk->uid;
+		selinux_get_task_sid(tsk, &audit_sig_sid);
 	}
 }

kernel/signal.c

@@ -23,12 +23,12 @@
 #include <linux/syscalls.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
-#include <linux/audit.h>
 #include <linux/capability.h>
 #include <asm/param.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/siginfo.h>
+#include "audit.h"	/* audit_signal_info() */
 
 /*
  * SLAB caches for signal bits.

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

security/selinux/ss/services.c

@@ -1980,7 +1980,7 @@ int selinux_audit_rule_match(u32 ctxid, u32 field, u32 op,
 		break;
 	case AUDIT_SE_SEN:
 	case AUDIT_SE_CLR:
-		level = (op == AUDIT_SE_SEN ?
+		level = (field == AUDIT_SE_SEN ?
 		         &ctxt->range.level[0] : &ctxt->range.level[1]);
 		switch (op) {
 		case AUDIT_EQUAL: