summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRobert Love <rml@novell.com>2005-07-13 01:06:03 +0400
committerLinus Torvalds <torvalds@g5.osdl.org>2005-07-13 07:38:38 +0400
commit0eeca28300df110bd6ed54b31193c83b87921443 (patch)
tree7db42d8a18d80eca538f5b7d25e0532b8fa38b85
parentbd4c625c061c2a38568d0add3478f59172455159 (diff)
downloadlinux-0eeca28300df110bd6ed54b31193c83b87921443.tar.xz
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly its inability to scale and its terrible user interface: * dnotify requires the opening of one fd per each directory that you intend to watch. This quickly results in too many open files and pins removable media, preventing unmount. * dnotify is directory-based. You only learn about changes to directories. Sure, a change to a file in a directory affects the directory, but you are then forced to keep a cache of stat structures. * dnotify's interface to user-space is awful. Signals? inotify provides a more usable, simple, powerful solution to file change notification: * inotify's interface is a system call that returns a fd, not SIGIO. You get a single fd, which is select()-able. * inotify has an event that says "the filesystem that the item you were watching is on was unmounted." * inotify can watch directories or files. Inotify is currently used by Beagle (a desktop search infrastructure), Gamin (a FAM replacement), and other projects. See Documentation/filesystems/inotify.txt. Signed-off-by: Robert Love <rml@novell.com> Cc: John McCutchan <ttb@tentacle.dhs.org> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--Documentation/filesystems/inotify.txt138
-rw-r--r--arch/i386/kernel/syscall_table.S3
-rw-r--r--fs/Kconfig13
-rw-r--r--fs/Makefile1
-rw-r--r--fs/attr.c33
-rw-r--r--fs/compat.c12
-rw-r--r--fs/file_table.c3
-rw-r--r--fs/inode.c6
-rw-r--r--fs/inotify.c999
-rw-r--r--fs/namei.c30
-rw-r--r--fs/nfsd/vfs.c6
-rw-r--r--fs/open.c3
-rw-r--r--fs/read_write.c15
-rw-r--r--fs/sysfs/file.c7
-rw-r--r--fs/xattr.c5
-rw-r--r--include/asm-i386/unistd.h5
-rw-r--r--include/linux/fs.h6
-rw-r--r--include/linux/fsnotify.h248
-rw-r--r--include/linux/inotify.h108
-rw-r--r--include/linux/sched.h4
-rw-r--r--include/linux/sysctl.h11
-rw-r--r--kernel/sys_ni.c3
-rw-r--r--kernel/sysctl.c43
-rw-r--r--kernel/user.c4
24 files changed, 1639 insertions, 67 deletions
diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.txt
new file mode 100644
index 000000000000..2c716041f578
--- /dev/null
+++ b/Documentation/filesystems/inotify.txt
@@ -0,0 +1,138 @@
+ inotify
+ a powerful yet simple file change notification system
+
+
+
+Document started 15 Mar 2005 by Robert Love <rml@novell.com>
+
+(i) User Interface
+
+Inotify is controlled by a set of three sys calls
+
+First step in using inotify is to initialise an inotify instance
+
+ int fd = inotify_init ();
+
+Change events are managed by "watches". A watch is an (object,mask) pair where
+the object is a file or directory and the mask is a bit mask of one or more
+inotify events that the application wishes to receive. See <linux/inotify.h>
+for valid events. A watch is referenced by a watch descriptor, or wd.
+
+Watches are added via a path to the file.
+
+Watches on a directory will return events on any files inside of the directory.
+
+Adding a watch is simple,
+
+ int wd = inotify_add_watch (fd, path, mask);
+
+You can add a large number of files via something like
+
+ for each file to watch {
+ int wd = inotify_add_watch (fd, file, mask);
+ }
+
+You can update an existing watch in the same manner, by passing in a new mask.
+
+An existing watch is removed via the INOTIFY_IGNORE ioctl, for example
+
+ inotify_rm_watch (fd, wd);
+
+Events are provided in the form of an inotify_event structure that is read(2)
+from a inotify instance fd. The filename is of dynamic length and follows the
+struct. It is of size len. The filename is padded with null bytes to ensure
+proper alignment. This padding is reflected in len.
+
+You can slurp multiple events by passing a large buffer, for example
+
+ size_t len = read (fd, buf, BUF_LEN);
+
+Will return as many events as are available and fit in BUF_LEN.
+
+each inotify instance fd is also select()- and poll()-able.
+
+You can find the size of the current event queue via the FIONREAD ioctl.
+
+All watches are destroyed and cleaned up on close.
+
+
+(ii) Internal Kernel Implementation
+
+Each open inotify instance is associated with an inotify_device structure.
+
+Each watch is associated with an inotify_watch structure. Watches are chained
+off of each associated device and each associated inode.
+
+See fs/inotify.c for the locking and lifetime rules.
+
+
+(iii) Rationale
+
+Q: What is the design decision behind not tying the watch to the open fd of
+ the watched object?
+
+A: Watches are associated with an open inotify device, not an open file.
+ This solves the primary problem with dnotify: keeping the file open pins
+ the file and thus, worse, pins the mount. Dnotify is therefore infeasible
+ for use on a desktop system with removable media as the media cannot be
+ unmounted.
+
+Q: What is the design decision behind using an-fd-per-device as opposed to
+ an fd-per-watch?
+
+A: An fd-per-watch quickly consumes more file descriptors than are allowed,
+ more fd's than are feasible to manage, and more fd's than are optimally
+ select()-able. Yes, root can bump the per-process fd limit and yes, users
+ can use epoll, but requiring both is a silly and extraneous requirement.
+ A watch consumes less memory than an open file, separating the number
+ spaces is thus sensible. The current design is what user-space developers
+ want: Users initialize inotify, once, and add n watches, requiring but one fd
+ and no twiddling with fd limits. Initializing an inotify instance two
+ thousand times is silly. If we can implement user-space's preferences
+ cleanly--and we can, the idr layer makes stuff like this trivial--then we
+ should.
+
+ There are other good arguments. With a single fd, there is a single
+ item to block on, which is mapped to a single queue of events. The single
+ fd returns all watch events and also any potential out-of-band data. If
+ every fd was a separate watch,
+
+ - There would be no way to get event ordering. Events on file foo and
+ file bar would pop poll() on both fd's, but there would be no way to tell
+ which happened first. A single queue trivially gives you ordering. Such
+ ordering is crucial to existing applications such as Beagle. Imagine
+ "mv a b ; mv b a" events without ordering.
+
+ - We'd have to maintain n fd's and n internal queues with state,
+ versus just one. It is a lot messier in the kernel. A single, linear
+ queue is the data structure that makes sense.
+
+ - User-space developers prefer the current API. The Beagle guys, for
+ example, love it. Trust me, I asked. It is not a surprise: Who'd want
+ to manage and block on 1000 fd's via select?
+
+ - You'd have to manage the fd's, as an example: Call close() when you
+ received a delete event.
+
+ - No way to get out of band data.
+
+ - 1024 is still too low. ;-)
+
+ When you talk about designing a file change notification system that
+ scales to 1000s of directories, juggling 1000s of fd's just does not seem
+ the right interface. It is too heavy.
+
+Q: Why the system call approach?
+
+A: The poor user-space interface is the second biggest problem with dnotify.
+ Signals are a terrible, terrible interface for file notification. Or for
+ anything, for that matter. The ideal solution, from all perspectives, is a
+ 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
+ features and it means our user interface requirements.
+
+ Additionally, it _is_ possible to more than one instance and
+ juggle more than one queue and thus more than one associated fd.
+
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 3db9a04aec6e..468500a7e894 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -291,3 +291,6 @@ ENTRY(sys_call_table)
.long sys_keyctl
.long sys_ioprio_set
.long sys_ioprio_get /* 290 */
+ .long sys_inotify_init
+ .long sys_inotify_add_watch
+ .long sys_inotify_rm_watch
diff --git a/fs/Kconfig b/fs/Kconfig
index f93fd41b025d..5d0c4be43dba 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -359,6 +359,19 @@ config ROMFS_FS
If you don't know whether you need it, then you don't need it:
answer N.
+config INOTIFY
+ bool "Inotify file change notification support"
+ default y
+ ---help---
+ Say Y here to enable inotify support and the /dev/inotify character
+ device. 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. Multiple file
+ events are supported.
+
+ If unsure, say Y.
+
config QUOTA
bool "Quota support"
help
diff --git a/fs/Makefile b/fs/Makefile
index 20edcf28bfd2..cf95eb894fd5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -12,6 +12,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \
seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
ioprio.o
+obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_COMPAT) += compat.o
diff --git a/fs/attr.c b/fs/attr.c
index c3c76fe78346..b1796fb9e524 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -10,7 +10,7 @@
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/quotaops.h>
#include <linux/security.h>
@@ -107,31 +107,8 @@ int inode_setattr(struct inode * inode, struct iattr * attr)
out:
return error;
}
-
EXPORT_SYMBOL(inode_setattr);
-int setattr_mask(unsigned int ia_valid)
-{
- unsigned long dn_mask = 0;
-
- if (ia_valid & ATTR_UID)
- dn_mask |= DN_ATTRIB;
- if (ia_valid & ATTR_GID)
- dn_mask |= DN_ATTRIB;
- if (ia_valid & ATTR_SIZE)
- dn_mask |= DN_MODIFY;
- /* both times implies a utime(s) call */
- if ((ia_valid & (ATTR_ATIME|ATTR_MTIME)) == (ATTR_ATIME|ATTR_MTIME))
- dn_mask |= DN_ATTRIB;
- else if (ia_valid & ATTR_ATIME)
- dn_mask |= DN_ACCESS;
- else if (ia_valid & ATTR_MTIME)
- dn_mask |= DN_MODIFY;
- if (ia_valid & ATTR_MODE)
- dn_mask |= DN_ATTRIB;
- return dn_mask;
-}
-
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
@@ -197,11 +174,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
if (ia_valid & ATTR_SIZE)
up_write(&dentry->d_inode->i_alloc_sem);
- if (!error) {
- unsigned long dn_mask = setattr_mask(ia_valid);
- if (dn_mask)
- dnotify_parent(dentry, dn_mask);
- }
+ if (!error)
+ fsnotify_change(dentry, ia_valid);
+
return error;
}
diff --git a/fs/compat.c b/fs/compat.c
index 728cd8365384..6b06b6bae35e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -37,7 +37,7 @@
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/dirent.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/highuid.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
@@ -1307,9 +1307,13 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
out:
if (iov != iovstack)
kfree(iov);
- if ((ret + (type == READ)) > 0)
- dnotify_parent(file->f_dentry,
- (type == READ) ? DN_ACCESS : DN_MODIFY);
+ if ((ret + (type == READ)) > 0) {
+ struct dentry *dentry = file->f_dentry;
+ if (type == READ)
+ fsnotify_access(dentry);
+ else
+ fsnotify_modify(dentry);
+ }
return ret;
}
diff --git a/fs/file_table.c b/fs/file_table.c
index fa7849fae134..1d3de78e6bc9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -16,6 +16,7 @@
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/cdev.h>
+#include <linux/fsnotify.h>
/* sysctl tunables... */
struct files_stat_struct files_stat = {
@@ -126,6 +127,8 @@ void fastcall __fput(struct file *file)
struct inode *inode = dentry->d_inode;
might_sleep();
+
+ fsnotify_close(file);
/*
* The function eventpoll_release() should be the first called
* in the file cleanup chain.
diff --git a/fs/inode.c b/fs/inode.c
index 5bc97507eeaa..96364fae0844 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -21,6 +21,7 @@
#include <linux/pagemap.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
+#include <linux/inotify.h>
/*
* This is needed for the following functions:
@@ -202,6 +203,10 @@ void inode_init_once(struct inode *inode)
INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
spin_lock_init(&inode->i_lock);
i_size_ordered_init(inode);
+#ifdef CONFIG_INOTIFY
+ INIT_LIST_HEAD(&inode->inotify_watches);
+ sema_init(&inode->inotify_sem, 1);
+#endif
}
EXPORT_SYMBOL(inode_init_once);
@@ -351,6 +356,7 @@ int invalidate_inodes(struct super_block * sb)
down(&iprune_sem);
spin_lock(&inode_lock);
+ inotify_unmount_inodes(&sb->s_inodes);
busy = invalidate_list(&sb->s_inodes, &throw_away);
spin_unlock(&inode_lock);
diff --git a/fs/inotify.c b/fs/inotify.c
new file mode 100644
index 000000000000..e423bfe0c86f
--- /dev/null
+++ b/fs/inotify.c
@@ -0,0 +1,999 @@
+/*
+ * fs/inotify.c - inode-based file event notifications
+ *
+ * Authors:
+ * John McCutchan <ttb@tentacle.dhs.org>
+ * Robert Love <rml@novell.com>
+ *
+ * Copyright (C) 2005 John McCutchan
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/writeback.h>
+#include <linux/inotify.h>
+
+#include <asm/ioctls.h>
+
+static atomic_t inotify_cookie;
+
+static kmem_cache_t *watch_cachep;
+static kmem_cache_t *event_cachep;
+
+static struct vfsmount *inotify_mnt;
+
+/* These are configurable via /proc/sys/inotify */
+int inotify_max_user_devices;
+int inotify_max_user_watches;
+int inotify_max_queued_events;
+
+/*
+ * Lock ordering:
+ *
+ * dentry->d_lock (used to keep d_move() away from dentry->d_parent)
+ * iprune_sem (synchronize shrink_icache_memory())
+ * inode_lock (protects the super_block->s_inodes list)
+ * inode->inotify_sem (protects inode->inotify_watches and watches->i_list)
+ * inotify_dev->sem (protects inotify_device and watches->d_list)
+ */
+
+/*
+ * Lifetimes of the three main data structures--inotify_device, inode, and
+ * inotify_watch--are managed by reference count.
+ *
+ * inotify_device: Lifetime is from open until release. Additional references
+ * can bump the count via get_inotify_dev() and drop the count via
+ * put_inotify_dev().
+ *
+ * inotify_watch: Lifetime is from create_watch() to destory_watch().
+ * Additional references can bump the count via get_inotify_watch() and drop
+ * the count via put_inotify_watch().
+ *
+ * inode: Pinned so long as the inode is associated with a watch, from
+ * create_watch() to put_inotify_watch().
+ */
+
+/*
+ * struct inotify_device - represents an open instance of an inotify device
+ *
+ * This structure is protected by the semaphore 'sem'.
+ */
+struct inotify_device {
+ wait_queue_head_t wq; /* wait queue for i/o */
+ struct idr idr; /* idr mapping wd -> watch */
+ struct semaphore sem; /* 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 */
+};
+
+/*
+ * 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->sem 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->sem of the associated watch->dev.
+ * i_list and mask are protected by inode->inotify_sem 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 */
+};
+
+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);
+ }
+}
+
+static inline void get_inotify_watch(struct inotify_watch *watch)
+{
+ atomic_inc(&watch->count);
+}
+
+/*
+ * put_inotify_watch - decrements the ref count on a given watch. cleans up
+ * the watch and its references if the count reaches zero.
+ */
+static inline 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->sem.
+ */
+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->sem. 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->sem.
+ */
+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->sem.
+ */
+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);
+ }
+}
+
+/*
+ * inotify_dev_get_wd - returns the next WD for use by the given dev
+ *
+ * Callers must hold dev->sem. This function can sleep.
+ */
+static int inotify_dev_get_wd(struct inotify_device *dev,
+ struct inotify_watch *watch)
+{
+ int ret;
+
+ do {
+ if (unlikely(!idr_pre_get(&dev->idr, GFP_KERNEL)))
+ return -ENOSPC;
+ ret = idr_get_new(&dev->idr, watch, &watch->wd);
+ } while (ret == -EAGAIN);
+
+ return ret;
+}
+
+/*
+ * 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)
+{
+ int error;
+
+ error = __user_walk(dirname, LOOKUP_FOLLOW, nd);
+ if (error)
+ return error;
+ /* you can only watch an inode if you have read permissions on it */
+ error = permission(nd->dentry->d_inode, MAY_READ, NULL);
+ if (error)
+ path_release (nd);
+ return error;
+}
+
+/*
+ * create_watch - creates a watch on the given device.
+ *
+ * Callers must hold dev->sem. 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);
+ }
+
+ 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
+ *
+ * Callers must hold inode->inotify_sem.
+ */
+static struct inotify_watch *inode_find_dev(struct inode *inode,
+ struct inotify_device *dev)
+{
+ struct inotify_watch *watch;
+
+ list_for_each_entry(watch, &inode->inotify_watches, i_list) {
+ if (watch->dev == dev)
+ return watch;
+ }
+
+ return NULL;
+}
+
+/*
+ * remove_watch_no_event - remove_watch() without the IN_IGNORED event.
+ */
+static void remove_watch_no_event(struct inotify_watch *watch,
+ struct inotify_device *dev)
+{
+ list_del(&watch->i_list);
+ list_del(&watch->d_list);
+
+ atomic_dec(&dev->user->inotify_watches);
+ idr_remove(&dev->idr, watch->wd);
+ put_inotify_watch(watch);
+}
+
+/*
+ * 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_sem and dev->sem. We drop a
+ * reference to the inode before returning.
+ *
+ * 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.
+ */
+static void remove_watch(struct inotify_watch *watch,struct inotify_device *dev)
+{
+ inotify_dev_queue_event(dev, watch, IN_IGNORED, 0, NULL);
+ remove_watch_no_event(watch, dev);
+}
+
+/*
+ * inotify_inode_watched - returns nonzero if there are watches on this inode
+ * and zero otherwise. We call this lockless, we do not care if we race.
+ */
+static inline int inotify_inode_watched(struct inode *inode)
+{
+ return !list_empty(&inode->inotify_watches);
+}
+
+/* Kernel API */
+
+/**
+ * inotify_inode_queue_event - queue an event to all watches on this inode
+ * @inode: inode event is originating from
+ * @mask: event mask describing this event
+ * @cookie: cookie for synchronization, or zero
+ * @name: filename, if any
+ */
+void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
+ const char *name)
+{
+ struct inotify_watch *watch, *next;
+
+ if (!inotify_inode_watched(inode))
+ return;
+
+ down(&inode->inotify_sem);
+ 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);
+ down(&dev->sem);
+ inotify_dev_queue_event(dev, watch, mask, cookie, name);
+ if (watch_mask & IN_ONESHOT)
+ remove_watch_no_event(watch, dev);
+ up(&dev->sem);
+ put_inotify_watch(watch);
+ }
+ }
+ up(&inode->inotify_sem);
+}
+EXPORT_SYMBOL_GPL(inotify_inode_queue_event);
+
+/**
+ * inotify_dentry_parent_queue_event - queue an event to a dentry's parent
+ * @dentry: the dentry in question, we queue against this dentry's parent
+ * @mask: event mask describing this event
+ * @cookie: cookie for synchronization, or zero
+ * @name: filename, if any
+ */
+void inotify_dentry_parent_queue_event(struct dentry *dentry, u32 mask,
+ u32 cookie, const char *name)
+{
+ struct dentry *parent;
+ struct inode *inode;
+
+ spin_lock(&dentry->d_lock);
+ parent = dentry->d_parent;
+ inode = parent->d_inode;
+
+ if (inotify_inode_watched(inode)) {
+ dget(parent);
+ spin_unlock(&dentry->d_lock);
+ inotify_inode_queue_event(inode, mask, cookie, name);
+ dput(parent);
+ } else
+ spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL_GPL(inotify_dentry_parent_queue_event);
+
+/**
+ * inotify_get_cookie - return a unique cookie for use in synchronizing events.
+ */
+u32 inotify_get_cookie(void)
+{
+ return atomic_inc_return(&inotify_cookie);
+}
+EXPORT_SYMBOL_GPL(inotify_get_cookie);
+
+/**
+ * inotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
+ * @list: list of inodes being unmounted (sb->s_inodes)
+ *
+ * Called with inode_lock held, protecting the unmounting super block's list
+ * of inodes, and with iprune_sem held, keeping shrink_icache_memory() at bay.
+ * We temporarily drop inode_lock, however, and CAN block.
+ */
+void inotify_unmount_inodes(struct list_head *list)
+{
+ struct inode *inode, *next_i, *need_iput = NULL;
+
+ list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+ struct inotify_watch *watch, *next_w;
+ struct inode *need_iput_tmp;
+ struct list_head *watches;
+
+ /*
+ * If i_count is zero, the inode cannot have any watches and
+ * doing an __iget/iput with MS_ACTIVE clear would actually
+ * evict all inodes with zero i_count from icache which is
+ * unnecessarily violent and may in fact be illegal to do.
+ */
+ if (!atomic_read(&inode->i_count))
+ continue;
+
+ /*
+ * We cannot __iget() an inode in state I_CLEAR, I_FREEING, or
+ * I_WILL_FREE which is fine because by that point the inode
+ * cannot have any associated watches.
+ */
+ if (inode->i_state & (I_CLEAR | I_FREEING | I_WILL_FREE))
+ continue;
+
+ need_iput_tmp = need_iput;
+ need_iput = NULL;
+ /* In case the remove_watch() drops a reference. */
+ if (inode != need_iput_tmp)
+ __iget(inode);
+ else
+ need_iput_tmp = NULL;
+ /* In case the dropping of a reference would nuke next_i. */
+ if ((&next_i->i_sb_list != list) &&
+ atomic_read(&next_i->i_count) &&
+ !(next_i->i_state & (I_CLEAR | I_FREEING |
+ I_WILL_FREE))) {
+ __iget(next_i);
+ need_iput = next_i;
+ }
+
+ /*
+ * We can safely drop inode_lock here because we hold
+ * references on both inode and next_i. Also no new inodes
+ * will be added since the umount has begun. Finally,
+ * iprune_sem keeps shrink_icache_memory() away.
+ */
+ spin_unlock(&inode_lock);
+
+ if (need_iput_tmp)
+ iput(need_iput_tmp);
+
+ /* for each watch, send IN_UNMOUNT and then remove it */
+ down(&inode->inotify_sem);
+ watches = &inode->inotify_watches;
+ list_for_each_entry_safe(watch, next_w, watches, i_list) {
+ struct inotify_device *dev = watch->dev;
+ down(&dev->sem);
+ inotify_dev_queue_event(dev, watch, IN_UNMOUNT,0,NULL);
+ remove_watch(watch, dev);
+ up(&dev->sem);
+ }
+ up(&inode->inotify_sem);
+ iput(inode);
+
+ spin_lock(&inode_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(inotify_unmount_inodes);
+
+/**
+ * inotify_inode_is_dead - an inode has been deleted, cleanup any watches
+ * @inode: inode that is about to be removed
+ */
+void inotify_inode_is_dead(struct inode *inode)
+{
+ struct inotify_watch *watch, *next;
+
+ down(&inode->inotify_sem);
+ list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
+ struct inotify_device *dev = watch->dev;
+ down(&dev->sem);
+ remove_watch(watch, dev);
+ up(&dev->sem);
+ }
+ up(&inode->inotify_sem);
+}
+EXPORT_SYMBOL_GPL(inotify_inode_is_dead);
+
+/* 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);
+ down(&dev->sem);
+ if (!list_empty(&dev->events))
+ ret = POLLIN | POLLRDNORM;
+ up(&dev->sem);
+
+ 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);
+
+ down(&dev->sem);
+ events = !list_empty(&dev->events);
+ up(&dev->sem);
+ 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;
+
+ down(&dev->sem);
+ 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);
+ }
+ up(&dev->sem);
+
+ return ret;
+}
+
+static int inotify_release(struct inode *ignored, struct file *file)
+{
+ struct inotify_device *dev = file->private_data;
+
+ /*
+ * Destroy all of the watches on this device. 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_sem before dev->sem. The following works.
+ */
+ while (1) {
+ struct inotify_watch *watch;
+ struct list_head *watches;
+ struct inode *inode;
+
+ down(&dev->sem);
+ watches = &dev->watches;
+ if (list_empty(watches)) {
+ up(&dev->sem);
+ break;
+ }
+ watch = list_entry(watches->next, struct inotify_watch, d_list);
+ get_inotify_watch(watch);
+ up(&dev->sem);
+
+ inode = watch->inode;
+ down(&inode->inotify_sem);
+ down(&dev->sem);
+ remove_watch_no_event(watch, dev);
+ up(&dev->sem);
+ up(&inode->inotify_sem);
+ put_inotify_watch(watch);
+ }
+
+ /* destroy all of the events on this device */
+ down(&dev->sem);
+ while (!list_empty(&dev->events))
+ inotify_dev_event_dequeue(dev);
+ up(&dev->sem);
+
+ /* free this device: the put matching the get in inotify_open() */
+ put_inotify_dev(dev);
+
+ return 0;
+}
+
+/*
+ * inotify_ignore - handle the INOTIFY_IGNORE ioctl, asking that a given wd be
+ * removed from the device.
+ *
+ * Can sleep.
+ */
+static int inotify_ignore(struct inotify_device *dev, s32 wd)
+{
+ struct inotify_watch *watch;
+ struct inode *inode;
+
+ down(&dev->sem);
+ watch = idr_find(&dev->idr, wd);
+ if (unlikely(!watch)) {
+ up(&dev->sem);
+ return -EINVAL;
+ }
+ get_inotify_watch(watch);
+ inode = watch->inode;
+ up(&dev->sem);
+
+ down(&inode->inotify_sem);
+ down(&dev->sem);
+
+ /* make sure that we did not race */
+ watch = idr_find(&dev->idr, wd);
+ if (likely(watch))
+ remove_watch(watch, dev);
+
+ up(&dev->sem);
+ up(&inode->inotify_sem);
+ put_inotify_watch(watch);
+
+ 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 struct file_operations inotify_fops = {
+ .poll = inotify_poll,
+ .read = inotify_read,
+ .release = inotify_release,
+ .unlocked_ioctl = inotify_ioctl,
+ .compat_ioctl = inotify_ioctl,
+};
+
+asmlinkage long sys_inotify_init(void)
+{
+ struct inotify_device *dev;
+ struct user_struct *user;
+ int ret = -ENOTTY;
+ int fd;
+ struct file *filp;
+
+ fd = get_unused_fd();
+ if (fd < 0) {
+ ret = fd;
+ goto out;
+ }
+
+ filp = get_empty_filp();
+ if (!filp) {
+ put_unused_fd(fd);
+ ret = -ENFILE;
+ 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;
+
+ user = get_uid(current->user);
+
+ if (unlikely(atomic_read(&user->inotify_devs) >= inotify_max_user_devices)) {
+ ret = -EMFILE;
+ goto out_err;
+ }
+
+ dev = kmalloc(sizeof(struct inotify_device), GFP_KERNEL);
+ if (unlikely(!dev)) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ idr_init(&dev->idr);
+ INIT_LIST_HEAD(&dev->events);
+ INIT_LIST_HEAD(&dev->watches);
+ init_waitqueue_head(&dev->wq);
+ sema_init(&dev->sem, 1);
+ 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);
+
+ filp->private_data = dev;
+ fd_install (fd, filp);
+ return fd;
+out_err:
+ put_unused_fd (fd);
+ put_filp (filp);
+ free_uid(user);
+out:
+ return ret;
+}
+
+asmlinkage long sys_inotify_add_watch(int fd, const char *path, u32 mask)
+{
+ struct inotify_watch *watch, *old;
+ struct inode *inode;
+ struct inotify_device *dev;
+ struct nameidata nd;
+ struct file *filp;
+ int ret;
+
+ filp = fget(fd);
+ if (!filp)
+ return -EBADF;
+
+ dev = filp->private_data;
+
+ ret = find_inode ((const char __user*)path, &nd);
+ if (ret)
+ goto fput_and_out;
+
+ /* Held in place by reference in nd */
+ inode = nd.dentry->d_inode;
+
+ down(&inode->inotify_sem);
+ down(&dev->sem);
+
+ /* don't let user-space set invalid bits: we don't want flags set */
+ mask &= IN_ALL_EVENTS;
+ if (!mask) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * 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.
+ */
+ old = inode_find_dev(inode, dev);
+ if (unlikely(old)) {
+ 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;
+ }
+
+ /* Add the watch to the device's and the inode's list */
+ list_add(&watch->d_list, &dev->watches);
+ list_add(&watch->i_list, &inode->inotify_watches);
+ ret = watch->wd;
+out:
+ path_release (&nd);
+ up(&dev->sem);
+ up(&inode->inotify_sem);
+fput_and_out:
+ fput(filp);
+ return ret;
+}
+
+asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
+{
+ struct file *filp;
+ struct inotify_device *dev;
+ int ret;
+
+ filp = fget(fd);
+ if (!filp)
+ return -EBADF;
+ dev = filp->private_data;
+ ret = inotify_ignore (dev, wd);
+ fput(filp);
+ 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_init - 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_init(void)
+{
+ register_filesystem(&inotify_fs_type);
+ inotify_mnt = kern_mount(&inotify_fs_type);
+
+ inotify_max_queued_events = 8192;
+ inotify_max_user_devices = 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);
+
+ printk(KERN_INFO "inotify syscall\n");
+
+ return 0;
+}
+
+module_init(inotify_init);
diff --git a/fs/namei.c b/fs/namei.c
index 1d93cb4f7c5f..02a824cd3c5c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -21,7 +21,7 @@
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/pagemap.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/smp_lock.h>
#include <linux/personality.h>
#include <linux/security.h>
@@ -1312,7 +1312,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
DQUOT_INIT(dir);
error = dir->i_op->create(dir, dentry, mode, nd);
if (!error) {
- inode_dir_notify(dir, DN_CREATE);
+ fsnotify_create(dir, dentry->d_name.name);
security_inode_post_create(dir, dentry, mode);
}
return error;
@@ -1637,7 +1637,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
DQUOT_INIT(dir);
error = dir->i_op->mknod(dir, dentry, mode, dev);
if (!error) {
- inode_dir_notify(dir, DN_CREATE);
+ fsnotify_create(dir, dentry->d_name.name);
security_inode_post_mknod(dir, dentry, mode, dev);
}
return error;
@@ -1710,7 +1710,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
DQUOT_INIT(dir);
error = dir->i_op->mkdir(dir, dentry, mode);
if (!error) {
- inode_dir_notify(dir, DN_CREATE);
+ fsnotify_mkdir(dir, dentry->d_name.name);
security_inode_post_mkdir(dir,dentry, mode);
}
return error;
@@ -1801,7 +1801,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
}
up(&dentry->d_inode->i_sem);
if (!error) {
- inode_dir_notify(dir, DN_DELETE);
+ fsnotify_rmdir(dentry, dentry->d_inode, dir);
d_delete(dentry);
}
dput(dentry);
@@ -1874,9 +1874,10 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
+ fsnotify_unlink(dentry, dir);
d_delete(dentry);
- inode_dir_notify(dir, DN_DELETE);
}
+
return error;
}
@@ -1950,7 +1951,7 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, i
DQUOT_INIT(dir);
error = dir->i_op->symlink(dir, dentry, oldname);
if (!error) {
- inode_dir_notify(dir, DN_CREATE);
+ fsnotify_create(dir, dentry->d_name.name);
security_inode_post_symlink(dir, dentry, oldname);
}
return error;
@@ -2023,7 +2024,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
error = dir->i_op->link(old_dentry, dir, new_dentry);
up(&old_dentry->d_inode->i_sem);
if (!error) {
- inode_dir_notify(dir, DN_CREATE);
+ fsnotify_create(dir, new_dentry->d_name.name);
security_inode_post_link(old_dentry, dir, new_dentry);
}
return error;
@@ -2187,6 +2188,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
{
int error;
int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
+ const char *old_name;
if (old_dentry->d_inode == new_dentry->d_inode)
return 0;
@@ -2208,18 +2210,18 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
DQUOT_INIT(old_dir);
DQUOT_INIT(new_dir);
+ old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+
if (is_dir)
error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
else
error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
if (!error) {
- if (old_dir == new_dir)
- inode_dir_notify(old_dir, DN_RENAME);
- else {
- inode_dir_notify(old_dir, DN_DELETE);
- inode_dir_notify(new_dir, DN_CREATE);
- }
+ const char *new_name = old_dentry->d_name.name;
+ fsnotify_move(old_dir, new_dir, old_name, new_name, is_dir);
}
+ fsnotify_oldname_free(old_name);
+
return error;
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5e0bf3917607..4f2cd3d27566 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -45,7 +45,7 @@
#endif /* CONFIG_NFSD_V3 */
#include <linux/nfsd/nfsfh.h>
#include <linux/quotaops.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#ifdef CONFIG_NFSD_V4
@@ -860,7 +860,7 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
nfsdstats.io_read += err;
*count = err;
err = 0;
- dnotify_parent(file->f_dentry, DN_ACCESS);
+ fsnotify_access(file->f_dentry);
} else
err = nfserrno(err);
out:
@@ -916,7 +916,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
set_fs(oldfs);
if (err >= 0) {
nfsdstats.io_write += cnt;
- dnotify_parent(file->f_dentry, DN_MODIFY);
+ fsnotify_modify(file->f_dentry);
}
/* clear setuid/setgid flag after write */
diff --git a/fs/open.c b/fs/open.c
index 3f4a4286fdc4..32bf05e2996d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -10,7 +10,7 @@
#include <linux/file.h>
#include <linux/smp_lock.h>
#include <linux/quotaops.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/tty.h>
@@ -951,6 +951,7 @@ asmlinkage long sys_open(const char __user * filename, int flags, int mode)
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
+ fsnotify_open(f->f_dentry);
fd_install(fd, f);
}
}
diff --git a/fs/read_write.c b/fs/read_write.c
index 9292f5fa4d62..563abd09b5c8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -10,7 +10,7 @@
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/smp_lock.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/syscalls.h>
@@ -252,7 +252,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
else
ret = do_sync_read(file, buf, count, pos);
if (ret > 0) {
- dnotify_parent(file->f_dentry, DN_ACCESS);
+ fsnotify_access(file->f_dentry);
current->rchar += ret;
}
current->syscr++;
@@ -303,7 +303,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
else
ret = do_sync_write(file, buf, count, pos);
if (ret > 0) {
- dnotify_parent(file->f_dentry, DN_MODIFY);
+ fsnotify_modify(file->f_dentry);
current->wchar += ret;
}
current->syscw++;
@@ -539,9 +539,12 @@ static ssize_t do_readv_writev(int type, struct file *file,
out:
if (iov != iovstack)
kfree(iov);
- if ((ret + (type == READ)) > 0)
- dnotify_parent(file->f_dentry,
- (type == READ) ? DN_ACCESS : DN_MODIFY);
+ if ((ret + (type == READ)) > 0) {
+ if (type == READ)
+ fsnotify_access(file->f_dentry);
+ else
+ fsnotify_modify(file->f_dentry);
+ }
return ret;
Efault:
ret = -EFAULT;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index d72c1ce48559..335288b9be0f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -3,7 +3,7 @@
*/
#include <linux/module.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
#include <linux/kobject.h>
#include <linux/namei.h>
#include <asm/uaccess.h>
@@ -391,9 +391,6 @@ int sysfs_create_file(struct kobject * kobj, const struct attribute * attr)
* sysfs_update_file - update the modified timestamp on an object attribute.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
- *
- * Also call dnotify for the dentry, which lots of userspace programs
- * use.
*/
int sysfs_update_file(struct kobject * kobj, const struct attribute * attr)
{
@@ -408,7 +405,7 @@ int sysfs_update_file(struct kobject * kobj, const struct attribute * attr)
if (victim->d_inode &&
(victim->d_parent->d_inode == dir->d_inode)) {
victim->d_inode->i_mtime = CURRENT_TIME;
- dnotify_parent(victim, DN_MODIFY);
+ fsnotify_modify(victim);
/**
* Drop reference from initial sysfs_get_dentry().
diff --git a/fs/xattr.c b/fs/xattr.c
index 93dee70a1dbe..6acd5c63da91 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -16,6 +16,7 @@
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/module.h>
+#include <linux/fsnotify.h>
#include <asm/uaccess.h>
/*
@@ -57,8 +58,10 @@ setxattr(struct dentry *d, char __user *name, void __user *value,
if (error)
goto out;
error = d->d_inode->i_op->setxattr(d, kname, kvalue, size, flags);
- if (!error)
+ if (!error) {
+ fsnotify_xattr(d);
security_inode_post_setxattr(d, kname, kvalue, size, flags);
+ }
out:
up(&d->d_inode->i_sem);
}
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index e25e4c71a879..a7cb377745bf 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -296,8 +296,11 @@
#define __NR_keyctl 288
#define __NR_ioprio_set 289
#define __NR_ioprio_get 290
+#define __NR_inotify_init 291
+#define __NR_inotify_add_watch 292
+#define __NR_inotify_rm_watch 293
-#define NR_syscalls 291
+#define NR_syscalls 294
/*
* user-visible error numbers are in the range -1 - -128: see
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 302ec20838ca..c9bf3746a9fb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -474,6 +474,11 @@ struct inode {
struct dnotify_struct *i_dnotify; /* for directory notifications */
#endif
+#ifdef CONFIG_INOTIFY
+ struct list_head inotify_watches; /* watches on this inode */
+ struct semaphore inotify_sem; /* protects the watches list */
+#endif
+
unsigned long i_state;
unsigned long dirtied_when; /* jiffies of first dirtying */
@@ -1393,7 +1398,6 @@ extern void emergency_remount(void);
extern int do_remount_sb(struct super_block *sb, int flags,
void *data, int force);
extern sector_t bmap(struct inode *, sector_t);
-extern int setattr_mask(unsigned int);
extern int notify_change(struct dentry *, struct iattr *);
extern int permission(struct inode *, int, struct nameidata *);
extern int generic_permission(struct inode *, int,
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
new file mode 100644
index 000000000000..eb581b6cfca9
--- /dev/null
+++ b/include/linux/fsnotify.h
@@ -0,0 +1,248 @@
+#ifndef _LINUX_FS_NOTIFY_H
+#define _LINUX_FS_NOTIFY_H
+
+/*
+ * include/linux/fsnotify.h - generic hooks for filesystem notification, to
+ * reduce in-source duplication from both dnotify and inotify.
+ *
+ * We don't compile any of this away in some complicated menagerie of ifdefs.
+ * Instead, we rely on the code inside to optimize away as needed.
+ *
+ * (C) Copyright 2005 Robert Love
+ */
+
+#ifdef __KERNEL__
+
+#include <linux/dnotify.h>
+#include <linux/inotify.h>
+
+/*
+ * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir
+ */
+static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
+ const char *old_name, const char *new_name,
+ int isdir)
+{
+ u32 cookie = inotify_get_cookie();
+
+ if (old_dir == new_dir)
+ inode_dir_notify(old_dir, DN_RENAME);
+ else {
+ inode_dir_notify(old_dir, DN_DELETE);
+ inode_dir_notify(new_dir, DN_CREATE);
+ }
+
+ 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);
+}
+
+/*
+ * fsnotify_unlink - file was unlinked
+ */
+static inline void fsnotify_unlink(struct dentry *dentry, struct inode *dir)
+{
+ struct inode *inode = dentry->d_inode;
+
+ inode_dir_notify(dir, DN_DELETE);
+ inotify_inode_queue_event(dir, IN_DELETE, 0, dentry->d_name.name);
+ inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL);
+
+ inotify_inode_is_dead(inode);
+}
+
+/*
+ * fsnotify_rmdir - directory was removed
+ */
+static inline void fsnotify_rmdir(struct dentry *dentry, struct inode *inode,
+ struct inode *dir)
+{
+ inode_dir_notify(dir, DN_DELETE);
+ inotify_inode_queue_event(dir,IN_DELETE|IN_ISDIR,0,dentry->d_name.name);
+ inotify_inode_queue_event(inode, IN_DELETE_SELF | IN_ISDIR, 0, NULL);
+ inotify_inode_is_dead(inode);
+}
+
+/*
+ * fsnotify_create - 'name' was linked in
+ */
+static inline void fsnotify_create(struct inode *inode, const char *name)
+{
+ inode_dir_notify(inode, DN_CREATE);
+ inotify_inode_queue_event(inode, IN_CREATE, 0, name);
+}
+
+/*
+ * fsnotify_mkdir - directory 'name' was created
+ */
+static inline void fsnotify_mkdir(struct inode *inode, const char *name)
+{
+ inode_dir_notify(inode, DN_CREATE);
+ inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, name);
+}
+
+/*
+ * fsnotify_access - file was read
+ */
+static inline void fsnotify_access(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+ u32 mask = IN_ACCESS;
+
+ if (S_ISDIR(inode->i_mode))
+ mask |= IN_ISDIR;
+
+ 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);
+}
+
+/*
+ * fsnotify_modify - file was modified
+ */
+static inline void fsnotify_modify(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+ u32 mask = IN_MODIFY;
+
+ if (S_ISDIR(inode->i_mode))
+ mask |= IN_ISDIR;
+
+ 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);
+}
+
+/*
+ * fsnotify_open - file was opened
+ */
+static inline void fsnotify_open(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+ u32 mask = IN_OPEN;
+
+ if (S_ISDIR(inode->i_mode))
+ mask |= IN_ISDIR;
+
+ inotify_inode_queue_event(inode, mask, 0, NULL);
+ inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+}
+
+/*
+ * fsnotify_close - file was closed
+ */
+static inline void fsnotify_close(struct file *file)
+{
+ struct dentry *dentry = file->f_dentry;
+ struct inode *inode = dentry->d_inode;
+ const char *name = dentry->d_name.name;
+ mode_t mode = file->f_mode;
+ u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
+
+ if (S_ISDIR(inode->i_mode))
+ mask |= IN_ISDIR;
+
+ inotify_dentry_parent_queue_event(dentry, mask, 0, name);
+ inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_xattr - extended attributes were changed
+ */
+static inline void fsnotify_xattr(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+ u32 mask = IN_ATTRIB;
+
+ if (S_ISDIR(inode->i_mode))
+ mask |= IN_ISDIR;
+
+ inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+ inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_change - notify_change event. file was modified and/or metadata
+ * was changed.
+ */
+static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
+{
+ struct inode *inode = dentry->d_inode;
+ int dn_mask = 0;
+ u32 in_mask = 0;
+
+ if (ia_valid & ATTR_UID) {
+ in_mask |= IN_ATTRIB;
+ dn_mask |= DN_ATTRIB;
+ }
+ if (ia_valid & ATTR_GID) {
+ in_mask |= IN_ATTRIB;
+ dn_mask |= DN_ATTRIB;
+ }
+ if (ia_valid & ATTR_SIZE) {
+ in_mask |= IN_MODIFY;
+ dn_mask |= DN_MODIFY;
+ }
+ /* both times implies a utime(s) call */
+ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME))
+ {
+ in_mask |= IN_ATTRIB;
+ dn_mask |= DN_ATTRIB;
+ } else if (ia_valid & ATTR_ATIME) {
+ in_mask |= IN_ACCESS;
+ dn_mask |= DN_ACCESS;
+ } else if (ia_valid & ATTR_MTIME) {
+ in_mask |= IN_MODIFY;
+ dn_mask |= DN_MODIFY;
+ }
+ if (ia_valid & ATTR_MODE) {
+ in_mask |= IN_ATTRIB;
+ dn_mask |= DN_ATTRIB;
+ }
+
+ if (dn_mask)
+ dnotify_parent(dentry, dn_mask);
+ if (in_mask) {
+ if (S_ISDIR(inode->i_mode))
+ in_mask |= IN_ISDIR;
+ inotify_inode_queue_event(inode, in_mask, 0, NULL);
+ inotify_dentry_parent_queue_event(dentry, in_mask, 0,
+ dentry->d_name.name);
+ }
+}
+
+#ifdef CONFIG_INOTIFY /* inotify helpers */
+
+/*
+ * fsnotify_oldname_init - save off the old filename before we change it
+ */
+static inline const char *fsnotify_oldname_init(const char *name)
+{
+ return kstrdup(name, GFP_KERNEL);
+}
+
+/*
+ * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init
+ */
+static inline void fsnotify_oldname_free(const char *old_name)
+{
+ kfree(old_name);
+}
+
+#else /* CONFIG_INOTIFY */
+
+static inline const char *fsnotify_oldname_init(const char *name)
+{
+ return NULL;
+}
+
+static inline void fsnotify_oldname_free(const char *old_name)
+{
+}
+
+#endif /* ! CONFIG_INOTIFY */
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/inotify.h b/include/linux/inotify.h
new file mode 100644
index 000000000000..a40c2bf0408e
--- /dev/null
+++ b/include/linux/inotify.h
@@ -0,0 +1,108 @@
+/*
+ * Inode based directory notification for Linux
+ *
+ * Copyright (C) 2005 John McCutchan
+ */
+
+#ifndef _LINUX_INOTIFY_H
+#define _LINUX_INOTIFY_H
+
+#include <linux/types.h>
+
+/*
+ * struct inotify_event - structure read from the inotify device for each event
+ *
+ * When you are watching a directory, you will receive the filename for events
+ * such as IN_CREATE, IN_DELETE, IN_OPEN, IN_CLOSE, ..., relative to the wd.
+ */
+struct inotify_event {
+ __s32 wd; /* watch descriptor */
+ __u32 mask; /* watch mask */
+ __u32 cookie; /* cookie to synchronize two events */
+ __u32 len; /* length (including nulls) of name */
+ char name[0]; /* stub for possible name */
+};
+
+/* the following are legal, implemented events that user-space can watch for */
+#define IN_ACCESS 0x00000001 /* File was accessed */
+#define IN_MODIFY 0x00000002 /* File was modified */
+#define IN_ATTRIB 0x00000004 /* Metadata changed */
+#define IN_CLOSE_WRITE 0x00000008 /* Writtable file was closed */
+#define IN_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */
+#define IN_OPEN 0x00000020 /* File was opened */
+#define IN_MOVED_FROM 0x00000040 /* File was moved from X */
+#define IN_MOVED_TO 0x00000080 /* File was moved to Y */
+#define IN_CREATE 0x00000100 /* Subfile was created */
+#define IN_DELETE 0x00000200 /* Subfile was deleted */
+#define IN_DELETE_SELF 0x00000400 /* Self was deleted */
+
+/* the following are legal events. they are sent as needed to any watch */
+#define IN_UNMOUNT 0x00002000 /* Backing fs was unmounted */
+#define IN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */
+#define IN_IGNORED 0x00008000 /* File was ignored */
+
+/* helper events */
+#define IN_CLOSE (IN_CLOSE_WRITE | IN_CLOSE_NOWRITE) /* close */
+#define IN_MOVE (IN_MOVED_FROM | IN_MOVED_TO) /* moves */
+
+/* special flags */
+#define IN_ISDIR 0x40000000 /* event occurred against dir */
+#define IN_ONESHOT 0x80000000 /* only send event once */
+
+/*
+ * All of the events - we build the list by hand so that we can add flags in
+ * the future and not break backward compatibility. Apps will get only the
+ * events that they originally wanted. Be sure to add new events here!
+ */
+#define IN_ALL_EVENTS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \
+ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \
+ IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF)
+
+#ifdef __KERNEL__
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/config.h>
+
+#ifdef CONFIG_INOTIFY
+
+extern void inotify_inode_queue_event(struct inode *, __u32, __u32,
+ const char *);
+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);
+
+#else
+
+static inline void inotify_inode_queue_event(struct inode *inode,
+ __u32 mask, __u32 cookie,
+ const char *filename)
+{
+}
+
+static inline void inotify_dentry_parent_queue_event(struct dentry *dentry,
+ __u32 mask, __u32 cookie,
+ const char *filename)
+{
+}
+
+static inline void inotify_unmount_inodes(struct list_head *list)
+{
+}
+
+static inline void inotify_inode_is_dead(struct inode *inode)
+{
+}
+
+static inline u32 inotify_get_cookie(void)
+{
+ return 0;
+}
+
+#endif /* CONFIG_INOTIFY */
+
+#endif /* __KERNEL __ */
+
+#endif /* _LINUX_INOTIFY_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ff48815bd3a2..dec5827c7742 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -410,6 +410,10 @@ 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
+ 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
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
unsigned long locked_shm; /* How many pages of mlocked shm ? */
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 5b5f434ac9a0..ce19a2aa0b21 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -61,7 +61,8 @@ enum
CTL_DEV=7, /* Devices */
CTL_BUS=8, /* Busses */
CTL_ABI=9, /* Binary emulation */
- CTL_CPU=10 /* CPU stuff (speed scaling, etc) */
+ CTL_CPU=10, /* CPU stuff (speed scaling, etc) */
+ CTL_INOTIFY=11 /* Inotify */
};
/* CTL_BUS names: */
@@ -70,6 +71,14 @@ enum
CTL_BUS_ISA=1 /* ISA */
};
+/* CTL_INOTIFY names: */
+enum
+{
+ INOTIFY_MAX_USER_DEVICES=1, /* max number of inotify device instances per user */
+ INOTIFY_MAX_USER_WATCHES=2, /* max number of inotify watches per user */
+ INOTIFY_MAX_QUEUED_EVENTS=3 /* Max number of queued events per inotify device instance */
+};
+
/* CTL_KERN names: */
enum
{
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 29196ce9b40f..42b40ae5eada 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -80,6 +80,9 @@ cond_syscall(sys_keyctl);
cond_syscall(compat_sys_keyctl);
cond_syscall(compat_sys_socketcall);
cond_syscall(sys_set_zone_reclaim);
+cond_syscall(sys_inotify_init);
+cond_syscall(sys_inotify_add_watch);
+cond_syscall(sys_inotify_rm_watch);
/* arch-specific weak syscall entries */
cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 270ee7fadbd8..b240e2cb86fc 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -67,6 +67,12 @@ extern int printk_ratelimit_jiffies;
extern int printk_ratelimit_burst;
extern int pid_max_min, pid_max_max;
+#ifdef CONFIG_INOTIFY
+extern int inotify_max_user_devices;
+extern int inotify_max_user_watches;
+extern int inotify_max_queued_events;
+#endif
+
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
int unknown_nmi_panic;
extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *,
@@ -218,6 +224,7 @@ static ctl_table root_table[] = {
.mode = 0555,
.child = dev_table,
},
+
{ .ctl_name = 0 }
};
@@ -959,6 +966,40 @@ static ctl_table fs_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+#ifdef CONFIG_INOTIFY
+ {
+ .ctl_name = INOTIFY_MAX_USER_DEVICES,
+ .procname = "max_user_devices",
+ .data = &inotify_max_user_devices,
+ .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
+ },
+#endif
{ .ctl_name = 0 }
};
@@ -968,7 +1009,7 @@ static ctl_table debug_table[] = {
static ctl_table dev_table[] = {
{ .ctl_name = 0 }
-};
+};
extern void init_irq_proc (void);
diff --git a/kernel/user.c b/kernel/user.c
index 734575d55769..89e562feb1b1 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -120,6 +120,10 @@ 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
+ atomic_set(&new->inotify_watches, 0);
+ atomic_set(&new->inotify_devs, 0);
+#endif
new->mq_bytes = 0;
new->locked_shm = 0;