* 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
#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 atomic_t inotify_watches;
+
+static kmem_cache_t *watch_cachep;
+static kmem_cache_t *event_cachep;
+
+static struct vfsmount *inotify_mnt;
+
+/* these are configurable via /proc/sys/fs/inotify/ */
+int inotify_max_user_instances;
+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_mutex (synchronize shrink_icache_memory())
+ * iprune_sem (synchronize shrink_icache_memory())
* inode_lock (protects the super_block->s_inodes list)
- * inode->inotify_mutex (protects inode->inotify_watches and watches->i_list)
- * inotify_handle->mutex (protects inotify_handle and watches->h_list)
- *
- * The inode->inotify_mutex and inotify_handle->mutex and held during execution
- * of a caller's event handler. Thus, the caller must not hold any locks
- * taken in their event handler while calling any of the published inotify
- * interfaces.
+ * 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_handle, inode, and
+ * Lifetimes of the three main data structures--inotify_device, inode, and
* inotify_watch--are managed by reference count.
*
- * inotify_handle: Lifetime is from inotify_init() to inotify_destroy().
- * Additional references can bump the count via get_inotify_handle() and drop
- * the count via put_inotify_handle().
+ * inotify_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_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.
+ * 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
- * inotify_add_watch() to the final put_inotify_watch().
+ * create_watch() to put_inotify_watch().
*/
/*
- * struct inotify_handle - represents an inotify instance
+ * struct inotify_device - represents an inotify instance
*
- * This structure is protected by the mutex 'mutex'.
+ * This structure is protected by the semaphore 'sem'.
*/
-struct inotify_handle {
+struct inotify_device {
+ wait_queue_head_t wq; /* wait queue for i/o */
struct idr idr; /* idr mapping wd -> watch */
- struct mutex mutex; /* protects this bad boy */
+ 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 */
u32 last_wd; /* the last wd allocated */
- const struct inotify_operations *in_ops; /* inotify caller operations */
};
-static inline void get_inotify_handle(struct inotify_handle *ih)
+/*
+ * 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 */
+};
+
+#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(&ih->count);
+ atomic_inc(&dev->count);
}
-static inline void put_inotify_handle(struct inotify_handle *ih)
+static inline void put_inotify_dev(struct inotify_device *dev)
{
- if (atomic_dec_and_test(&ih->count)) {
- idr_destroy(&ih->idr);
- kfree(ih);
+ if (atomic_dec_and_test(&dev->count)) {
+ atomic_dec(&dev->user->inotify_devs);
+ free_uid(dev->user);
+ idr_destroy(&dev->idr);
+ kfree(dev);
}
}
-/**
- * get_inotify_watch - grab a reference to an inotify_watch
- * @watch: watch to grab
- */
-void get_inotify_watch(struct inotify_watch *watch)
+static inline 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
- * watch references if the count reaches zero. inotify_watch is freed by
- * inotify callers via the destroy_watch() op.
- * @watch: watch to release
+ * the watch and its references if the count reaches zero.
*/
-void put_inotify_watch(struct inotify_watch *watch)
+static inline void put_inotify_watch(struct inotify_watch *watch)
{
if (atomic_dec_and_test(&watch->count)) {
- struct inotify_handle *ih = watch->ih;
-
+ put_inotify_dev(watch->dev);
iput(watch->inode);
- ih->in_ops->destroy_watch(watch);
- put_inotify_handle(ih);
+ kmem_cache_free(watch_cachep, watch);
}
}
-EXPORT_SYMBOL_GPL(put_inotify_watch);
/*
- * inotify_handle_get_wd - returns the next WD for use by the given handle
+ * kernel_event - create a new kernel event with the given parameters
*
- * Callers must hold ih->mutex. This function can sleep.
+ * This function can sleep.
*/
-static int inotify_handle_get_wd(struct inotify_handle *ih,
- struct inotify_watch *watch)
+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(&ih->idr, GFP_KERNEL)))
+ if (unlikely(!idr_pre_get(&dev->idr, GFP_KERNEL)))
return -ENOSPC;
- ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
+ ret = idr_get_new_above(&dev->idr, watch, dev->last_wd+1, &watch->wd);
} while (ret == -EAGAIN);
- if (likely(!ret))
- ih->last_wd = watch->wd;
-
return ret;
}
/*
- * inotify_inode_watched - returns nonzero if there are watches on this inode
- * and zero otherwise. We call this lockless, we do not care if we race.
+ * find_inode - resolve a user-given path to a specific inode and return a nd
*/
-static inline int inotify_inode_watched(struct inode *inode)
+static int find_inode(const char __user *dirname, struct nameidata *nd,
+ unsigned flags)
{
- return !list_empty(&inode->inotify_watches);
+ 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;
}
/*
- * Get child dentry flag into synch with parent inode.
- * Flag should always be clear for negative dentrys.
+ * 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 void set_dentry_child_flags(struct inode *inode, int watched)
+static struct inotify_watch *create_watch(struct inotify_device *dev,
+ u32 mask, struct inode *inode)
{
- struct dentry *alias;
+ struct inotify_watch *watch;
+ int ret;
- spin_lock(&dcache_lock);
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
- struct dentry *child;
+ if (atomic_read(&dev->user->inotify_watches) >=
+ inotify_max_user_watches)
+ return ERR_PTR(-ENOSPC);
- list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
- if (!child->d_inode) {
- WARN_ON(child->d_flags & DCACHE_INOTIFY_PARENT_WATCHED);
- continue;
- }
- spin_lock(&child->d_lock);
- if (watched) {
- WARN_ON(child->d_flags &
- DCACHE_INOTIFY_PARENT_WATCHED);
- child->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
- } else {
- WARN_ON(!(child->d_flags &
- DCACHE_INOTIFY_PARENT_WATCHED));
- child->d_flags&=~DCACHE_INOTIFY_PARENT_WATCHED;
- }
- spin_unlock(&child->d_lock);
- }
+ 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);
}
- spin_unlock(&dcache_lock);
+
+ 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);
+ atomic_inc(&inotify_watches);
+
+ return watch;
}
/*
- * inotify_find_handle - find the watch associated with the given inode and
- * handle
+ * inotify_find_dev - find the watch associated with the given inode and dev
*
- * Callers must hold inode->inotify_mutex.
+ * Callers must hold inode->inotify_sem.
*/
-static struct inotify_watch *inode_find_handle(struct inode *inode,
- struct inotify_handle *ih)
+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->ih == ih)
+ if (watch->dev == dev)
return watch;
}
}
/*
- * remove_watch_no_event - remove watch without the IN_IGNORED event.
- *
- * Callers must hold both inode->inotify_mutex and ih->mutex.
+ * remove_watch_no_event - remove_watch() without the IN_IGNORED event.
*/
static void remove_watch_no_event(struct inotify_watch *watch,
- struct inotify_handle *ih)
+ struct inotify_device *dev)
{
list_del(&watch->i_list);
- list_del(&watch->h_list);
-
- if (!inotify_inode_watched(watch->inode))
- set_dentry_child_flags(watch->inode, 0);
+ list_del(&watch->d_list);
- idr_remove(&ih->idr, watch->wd);
+ atomic_dec(&dev->user->inotify_watches);
+ atomic_dec(&inotify_watches);
+ idr_remove(&dev->idr, watch->wd);
+ put_inotify_watch(watch);
}
-/**
- * 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
+/*
+ * 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.
*
- * Callers must hold both inode->inotify_mutex and ih->mutex.
+ * 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.
*/
-void inotify_remove_watch_locked(struct inotify_handle *ih,
- struct inotify_watch *watch)
+static void remove_watch(struct inotify_watch *watch,struct inotify_device *dev)
{
- remove_watch_no_event(watch, ih);
- ih->in_ops->handle_event(watch, watch->wd, IN_IGNORED, 0, NULL, NULL);
+ inotify_dev_queue_event(dev, watch, IN_IGNORED, 0, NULL);
+ remove_watch_no_event(watch, dev);
}
-EXPORT_SYMBOL_GPL(inotify_remove_watch_locked);
-
-/* Kernel API for producing events */
/*
- * inotify_d_instantiate - instantiate dcache entry for inode
+ * 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.
*/
-void inotify_d_instantiate(struct dentry *entry, struct inode *inode)
+static inline int inotify_inode_watched(struct inode *inode)
{
- struct dentry *parent;
-
- if (!inode)
- return;
-
- WARN_ON(entry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED);
- spin_lock(&entry->d_lock);
- parent = entry->d_parent;
- if (parent->d_inode && inotify_inode_watched(parent->d_inode))
- entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
- spin_unlock(&entry->d_lock);
+ return !list_empty(&inode->inotify_watches);
}
-/*
- * inotify_d_move - dcache entry has been moved
- */
-void inotify_d_move(struct dentry *entry)
-{
- struct dentry *parent;
-
- parent = entry->d_parent;
- if (inotify_inode_watched(parent->d_inode))
- entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
- else
- entry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED;
-}
+/* Kernel API */
/**
* inotify_inode_queue_event - queue an event to all watches on this inode
* @mask: event mask describing this event
* @cookie: cookie for synchronization, or zero
* @name: filename, if any
- * @n_inode: inode associated with name
*/
void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
- const char *name, struct inode *n_inode)
+ const char *name)
{
struct inotify_watch *watch, *next;
if (!inotify_inode_watched(inode))
return;
- mutex_lock(&inode->inotify_mutex);
+ 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_handle *ih= watch->ih;
- mutex_lock(&ih->mutex);
+ 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, ih);
- ih->in_ops->handle_event(watch, watch->wd, mask, cookie,
- name, n_inode);
- mutex_unlock(&ih->mutex);
+ remove_watch_no_event(watch, dev);
+ up(&dev->sem);
+ put_inotify_watch(watch);
}
}
- mutex_unlock(&inode->inotify_mutex);
+ up(&inode->inotify_sem);
}
EXPORT_SYMBOL_GPL(inotify_inode_queue_event);
struct dentry *parent;
struct inode *inode;
- if (!(dentry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED))
+ if (!atomic_read (&inotify_watches))
return;
spin_lock(&dentry->d_lock);
if (inotify_inode_watched(inode)) {
dget(parent);
spin_unlock(&dentry->d_lock);
- inotify_inode_queue_event(inode, mask, cookie, name,
- dentry->d_inode);
+ inotify_inode_queue_event(inode, mask, cookie, name);
dput(parent);
} else
spin_unlock(&dentry->d_lock);
* @list: list of inodes being unmounted (sb->s_inodes)
*
* Called with inode_lock held, protecting the unmounting super block's list
- * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
+ * 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)
need_iput_tmp = need_iput;
need_iput = NULL;
- /* In case inotify_remove_watch_locked() drops a reference. */
+ /* In case the remove_watch() drops a reference. */
if (inode != need_iput_tmp)
__iget(inode);
else
* We can safely drop inode_lock here because we hold
* references on both inode and next_i. Also no new inodes
* will be added since the umount has begun. Finally,
- * iprune_mutex keeps shrink_icache_memory() away.
+ * iprune_sem keeps shrink_icache_memory() away.
*/
spin_unlock(&inode_lock);
iput(need_iput_tmp);
/* for each watch, send IN_UNMOUNT and then remove it */
- mutex_lock(&inode->inotify_mutex);
+ down(&inode->inotify_sem);
watches = &inode->inotify_watches;
list_for_each_entry_safe(watch, next_w, watches, i_list) {
- 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);
+ 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);
}
- mutex_unlock(&inode->inotify_mutex);
+ up(&inode->inotify_sem);
iput(inode);
spin_lock(&inode_lock);
{
struct inotify_watch *watch, *next;
- mutex_lock(&inode->inotify_mutex);
+ down(&inode->inotify_sem);
list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
- struct inotify_handle *ih = watch->ih;
- mutex_lock(&ih->mutex);
- inotify_remove_watch_locked(ih, watch);
- mutex_unlock(&ih->mutex);
+ struct inotify_device *dev = watch->dev;
+ down(&dev->sem);
+ remove_watch(watch, dev);
+ up(&dev->sem);
}
- mutex_unlock(&inode->inotify_mutex);
+ up(&inode->inotify_sem);
}
EXPORT_SYMBOL_GPL(inotify_inode_is_dead);
-/* Kernel Consumer API */
+/* Device Interface */
-/**
- * inotify_init - allocate and initialize an inotify instance
- * @ops: caller's inotify operations
- */
-struct inotify_handle *inotify_init(const struct inotify_operations *ops)
+static unsigned int inotify_poll(struct file *file, poll_table *wait)
{
- struct inotify_handle *ih;
-
- ih = kmalloc(sizeof(struct inotify_handle), GFP_KERNEL);
- if (unlikely(!ih))
- return ERR_PTR(-ENOMEM);
+ struct inotify_device *dev = file->private_data;
+ int ret = 0;
- 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);
+ poll_wait(file, &dev->wq, wait);
+ down(&dev->sem);
+ if (!list_empty(&dev->events))
+ ret = POLLIN | POLLRDNORM;
+ up(&dev->sem);
- return ih;
+ return ret;
}
-EXPORT_SYMBOL_GPL(inotify_init);
-/**
- * inotify_init_watch - initialize an inotify watch
- * @watch: watch to initialize
- */
-void inotify_init_watch(struct inotify_watch *watch)
+static ssize_t inotify_read(struct file *file, char __user *buf,
+ size_t count, loff_t *pos)
{
- INIT_LIST_HEAD(&watch->h_list);
- INIT_LIST_HEAD(&watch->i_list);
- atomic_set(&watch->count, 0);
- get_inotify_watch(watch); /* initial get */
+ 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;
}
-EXPORT_SYMBOL_GPL(inotify_init_watch);
-/**
- * inotify_destroy - clean up and destroy an inotify instance
- * @ih: inotify handle
- */
-void inotify_destroy(struct inotify_handle *ih)
+static int inotify_release(struct inode *ignored, struct file *file)
{
+ struct inotify_device *dev = file->private_data;
+
/*
- * Destroy all of the watches for this handle. Unfortunately, not very
+ * 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_mutex before ih->mutex. The following works.
+ * hold inode->inotify_sem before dev->sem. The following works.
*/
while (1) {
struct inotify_watch *watch;
struct list_head *watches;
struct inode *inode;
- mutex_lock(&ih->mutex);
- watches = &ih->watches;
+ down(&dev->sem);
+ watches = &dev->watches;
if (list_empty(watches)) {
- mutex_unlock(&ih->mutex);
+ up(&dev->sem);
break;
}
- watch = list_entry(watches->next, struct inotify_watch, h_list);
+ watch = list_entry(watches->next, struct inotify_watch, d_list);
get_inotify_watch(watch);
- mutex_unlock(&ih->mutex);
+ up(&dev->sem);
inode = watch->inode;
- mutex_lock(&inode->inotify_mutex);
- mutex_lock(&ih->mutex);
-
- /* make sure we didn't race with another list removal */
- if (likely(idr_find(&ih->idr, watch->wd))) {
- remove_watch_no_event(watch, ih);
- put_inotify_watch(watch);
- }
-
- mutex_unlock(&ih->mutex);
- mutex_unlock(&inode->inotify_mutex);
+ down(&inode->inotify_sem);
+ down(&dev->sem);
+ remove_watch_no_event(watch, dev);
+ up(&dev->sem);
+ up(&inode->inotify_sem);
put_inotify_watch(watch);
}
- /* free this handle: the put matching the get in inotify_init() */
- put_inotify_handle(ih);
+ /* 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_init() */
+ put_inotify_dev(dev);
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(inotify_destroy);
-/**
- * inotify_find_watch - find an existing watch for an (ih,inode) pair
- * @ih: inotify handle
- * @inode: inode to watch
- * @watchp: pointer to existing inotify_watch
+/*
+ * inotify_ignore - remove a given wd from this inotify instance.
*
- * Caller must pin given inode (via nameidata).
+ * Can sleep.
*/
-s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
- struct inotify_watch **watchp)
+static int inotify_ignore(struct inotify_device *dev, s32 wd)
{
- struct inotify_watch *old;
- int ret = -ENOENT;
-
- mutex_lock(&inode->inotify_mutex);
- mutex_lock(&ih->mutex);
+ struct inotify_watch *watch;
+ struct inode *inode;
- old = inode_find_handle(inode, ih);
- if (unlikely(old)) {
- get_inotify_watch(old); /* caller must put watch */
- *watchp = old;
- ret = old->wd;
+ 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);
- mutex_unlock(&ih->mutex);
- mutex_unlock(&inode->inotify_mutex);
+ down(&inode->inotify_sem);
+ down(&dev->sem);
- return ret;
+ /* 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;
}
-EXPORT_SYMBOL_GPL(inotify_find_watch);
-/**
- * inotify_find_update_watch - find and update the mask of an existing watch
- * @ih: inotify handle
- * @inode: inode's watch to update
- * @mask: mask of events to watch
- *
- * Caller must pin given inode (via nameidata).
- */
-s32 inotify_find_update_watch(struct inotify_handle *ih, struct inode *inode,
- u32 mask)
+static long inotify_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
{
- struct inotify_watch *old;
- int mask_add = 0;
- int ret;
+ struct inotify_device *dev;
+ void __user *p;
+ int ret = -ENOTTY;
- if (mask & IN_MASK_ADD)
- mask_add = 1;
+ dev = file->private_data;
+ p = (void __user *) arg;
- /* don't allow invalid bits: we don't want flags set */
- mask &= IN_ALL_EVENTS | IN_ONESHOT;
- if (unlikely(!mask))
- return -EINVAL;
+ switch (cmd) {
+ case FIONREAD:
+ ret = put_user(dev->queue_size, (int __user *) p);
+ break;
+ }
- mutex_lock(&inode->inotify_mutex);
- mutex_lock(&ih->mutex);
+ return ret;
+}
- /*
- * 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;
+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;
+ 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;
}
- if (mask_add)
- old->mask |= mask;
- else
- old->mask = mask;
- ret = old->wd;
-out:
- mutex_unlock(&ih->mutex);
- mutex_unlock(&inode->inotify_mutex);
+ 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;
+ }
+
+ 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);
+ sema_init(&dev->sem, 1);
+ 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);
return ret;
}
-EXPORT_SYMBOL_GPL(inotify_find_update_watch);
-/**
- * inotify_add_watch - add a watch to an inotify instance
- * @ih: inotify handle
- * @watch: caller allocated watch structure
- * @inode: inode to watch
- * @mask: mask of events to watch
- *
- * Caller must pin given inode (via nameidata).
- * Caller must ensure it only calls inotify_add_watch() once per watch.
- * Calls inotify_handle_get_wd() so may sleep.
- */
-s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch,
- struct inode *inode, u32 mask)
+asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
{
- int ret = 0;
+ 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;
- /* 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;
+ 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;
+ }
- mutex_lock(&inode->inotify_mutex);
- mutex_lock(&ih->mutex);
+ if (!(mask & IN_DONT_FOLLOW))
+ flags |= LOOKUP_FOLLOW;
+ if (mask & IN_ONLYDIR)
+ flags |= LOOKUP_DIRECTORY;
- /* Initialize a new watch */
- ret = inotify_handle_get_wd(ih, watch);
+ ret = find_inode(path, &nd, flags);
if (unlikely(ret))
- goto out;
- ret = watch->wd;
+ 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;
- /* save a reference to handle and bump the count to make it official */
- get_inotify_handle(ih);
- watch->ih = ih;
+ down(&inode->inotify_sem);
+ down(&dev->sem);
+
+ if (mask & IN_MASK_ADD)
+ mask_add = 1;
+
+ /* 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;
+ goto out;
+ }
/*
- * 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.
+ * 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.
*/
- watch->inode = igrab(inode);
+ old = inode_find_dev(inode, dev);
+ if (unlikely(old)) {
+ if (mask_add)
+ old->mask |= mask;
+ else
+ old->mask = mask;
+ ret = old->wd;
+ goto out;
+ }
- if (!inotify_inode_watched(inode))
- set_dentry_child_flags(inode, 1);
+ watch = create_watch(dev, mask, inode);
+ if (unlikely(IS_ERR(watch))) {
+ ret = PTR_ERR(watch);
+ goto out;
+ }
- /* Add the watch to the handle's and the inode's list */
- list_add(&watch->h_list, &ih->watches);
+ /* 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:
- mutex_unlock(&ih->mutex);
- mutex_unlock(&inode->inotify_mutex);
+ up(&dev->sem);
+ up(&inode->inotify_sem);
+ path_release(&nd);
+fput_and_out:
+ fput_light(filp, fput_needed);
return ret;
}
-EXPORT_SYMBOL_GPL(inotify_add_watch);
-/**
- * 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)
+asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
{
- struct inotify_watch *watch;
- struct inode *inode;
+ struct file *filp;
+ struct inotify_device *dev;
+ int ret, fput_needed;
- 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);
+ filp = fget_light(fd, &fput_needed);
+ if (unlikely(!filp))
+ return -EBADF;
- mutex_lock(&inode->inotify_mutex);
- mutex_lock(&ih->mutex);
-
- /* make sure that we did not race */
- if (likely(idr_find(&ih->idr, wd) == watch))
- inotify_remove_watch_locked(ih, watch);
+ /* verify that this is indeed an inotify instance */
+ if (unlikely(filp->f_op != &inotify_fops)) {
+ ret = -EINVAL;
+ goto out;
+ }
- mutex_unlock(&ih->mutex);
- mutex_unlock(&inode->inotify_mutex);
- put_inotify_watch(watch);
+ dev = filp->private_data;
+ ret = inotify_ignore(dev, wd);
- return 0;
+out:
+ fput_light(filp, fput_needed);
+ return ret;
}
-EXPORT_SYMBOL_GPL(inotify_rm_wd);
-/**
- * inotify_rm_watch - remove a watch from an inotify instance
- * @ih: inotify handle
- * @watch: watch to remove
- *
- * Can sleep.
- */
-int inotify_rm_watch(struct inotify_handle *ih,
- struct inotify_watch *watch)
+static struct super_block *
+inotify_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data)
{
- return inotify_rm_wd(ih, watch->wd);
+ return get_sb_pseudo(fs_type, "inotify", NULL, 0xBAD1DEA);
}
-EXPORT_SYMBOL_GPL(inotify_rm_watch);
+
+static struct file_system_type inotify_fs_type = {
+ .name = "inotifyfs",
+ .get_sb = inotify_get_sb,
+ .kill_sb = kill_anon_super,
+};
/*
- * inotify_setup - core initialization function
+ * 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().
*/
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);
+ atomic_set(&inotify_watches, 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;
}
git://git.onelab.eu / linux-2.6.git / blobdiff