Commit 2d9048e2 authored by Amy Griffis's avatar Amy Griffis Committed by Al Viro
Browse files

[PATCH] inotify (1/5): split kernel API from userspace support



The following series of patches introduces a kernel API for inotify,
making it possible for kernel modules to benefit from inotify's
mechanism for watching inodes.  With these patches, inotify will
maintain for each caller a list of watches (via an embedded struct
inotify_watch), where each inotify_watch is associated with a
corresponding struct inode.  The caller registers an event handler and
specifies for which filesystem events their event handler should be
called per inotify_watch.
Signed-off-by: default avatarAmy Griffis <amy.griffis@hp.com>
Acked-by: default avatarRobert Love <rml@novell.com>
Acked-by: default avatarJohn McCutchan <john@johnmccutchan.com>
Signed-off-by: default avatarAl Viro <viro@zeniv.linux.org.uk>
parent 90204e0b
......@@ -393,18 +393,30 @@ config INOTIFY
bool "Inotify file change notification support"
default y
---help---
Say Y here to enable inotify support and the associated system
calls. Inotify is a file change notification system and a
replacement for dnotify. Inotify fixes numerous shortcomings in
dnotify and introduces several new features. It allows monitoring
of both files and directories via a single open fd. Other features
include multiple file events, one-shot support, and unmount
Say Y here to enable inotify support. Inotify is a file change
notification system and a replacement for dnotify. Inotify fixes
numerous shortcomings in dnotify and introduces several new features
including multiple file events, one-shot support, and unmount
notification.
For more information, see Documentation/filesystems/inotify.txt
If unsure, say Y.
config INOTIFY_USER
bool "Inotify support for userspace"
depends on INOTIFY
default y
---help---
Say Y here to enable inotify support for userspace, including the
associated system calls. Inotify allows monitoring of both files and
directories via a single open fd. Events are read from the file
descriptor, which is also select()- and poll()-able.
For more information, see Documentation/filesystems/inotify.txt
If unsure, say Y.
config QUOTA
bool "Quota support"
help
......
......@@ -13,6 +13,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \
ioprio.o pnode.o drop_caches.o splice.o sync.o
obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o
......
......@@ -5,7 +5,10 @@
* John McCutchan <ttb@tentacle.dhs.org>
* Robert Love <rml@novell.com>
*
* Kernel API added by: Amy Griffis <amy.griffis@hp.com>
*
* Copyright (C) 2005 John McCutchan
* Copyright 2006 Hewlett-Packard Development Company, L.P.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
......@@ -20,35 +23,17 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/writeback.h>
#include <linux/inotify.h>
#include <linux/syscalls.h>
#include <asm/ioctls.h>
static atomic_t inotify_cookie;
static kmem_cache_t *watch_cachep __read_mostly;
static kmem_cache_t *event_cachep __read_mostly;
static struct vfsmount *inotify_mnt __read_mostly;
/* these are configurable via /proc/sys/fs/inotify/ */
int inotify_max_user_instances __read_mostly;
int inotify_max_user_watches __read_mostly;
int inotify_max_queued_events __read_mostly;
/*
* Lock ordering:
*
......@@ -56,327 +41,108 @@ int inotify_max_queued_events __read_mostly;
* iprune_mutex (synchronize shrink_icache_memory())
* inode_lock (protects the super_block->s_inodes list)
* inode->inotify_mutex (protects inode->inotify_watches and watches->i_list)
* inotify_dev->mutex (protects inotify_device and watches->d_list)
* inotify_handle->mutex (protects inotify_handle and watches->h_list)
*
* The inode->inotify_mutex and inotify_handle->mutex and held during execution
* of a caller's event handler. Thus, the caller must not hold any locks
* taken in their event handler while calling any of the published inotify
* interfaces.
*/
/*
* Lifetimes of the three main data structures--inotify_device, inode, and
* Lifetimes of the three main data structures--inotify_handle, inode, and
* inotify_watch--are managed by reference count.
*
* inotify_device: Lifetime is from inotify_init() until release. Additional
* references can bump the count via get_inotify_dev() and drop the count via
* put_inotify_dev().
* inotify_handle: Lifetime is from inotify_init() to inotify_destroy().
* Additional references can bump the count via get_inotify_handle() and drop
* the count via put_inotify_handle().
*
* inotify_watch: Lifetime is from create_watch() to destory_watch().
* Additional references can bump the count via get_inotify_watch() and drop
* the count via put_inotify_watch().
* inotify_watch: for inotify's purposes, lifetime is from inotify_add_watch()
* to remove_watch_no_event(). Additional references can bump the count via
* get_inotify_watch() and drop the count via put_inotify_watch(). The caller
* is reponsible for the final put after receiving IN_IGNORED, or when using
* IN_ONESHOT after receiving the first event. Inotify does the final put if
* inotify_destroy() is called.
*
* inode: Pinned so long as the inode is associated with a watch, from
* create_watch() to put_inotify_watch().
* inotify_add_watch() to the final put_inotify_watch().
*/
/*
* struct inotify_device - represents an inotify instance
* struct inotify_handle - represents an inotify instance
*
* This structure is protected by the mutex 'mutex'.
*/
struct inotify_device {
wait_queue_head_t wq; /* wait queue for i/o */
struct inotify_handle {
struct idr idr; /* idr mapping wd -> watch */
struct mutex mutex; /* protects this bad boy */
struct list_head events; /* list of queued events */
struct list_head watches; /* list of watches */
atomic_t count; /* reference count */
struct user_struct *user; /* user who opened this dev */
unsigned int queue_size; /* size of the queue (bytes) */
unsigned int event_count; /* number of pending events */
unsigned int max_events; /* maximum number of events */
u32 last_wd; /* the last wd allocated */
const struct inotify_operations *in_ops; /* inotify caller operations */
};
/*
* struct inotify_kernel_event - An inotify event, originating from a watch and
* queued for user-space. A list of these is attached to each instance of the
* device. In read(), this list is walked and all events that can fit in the
* buffer are returned.
*
* Protected by dev->mutex of the device in which we are queued.
*/
struct inotify_kernel_event {
struct inotify_event event; /* the user-space event */
struct list_head list; /* entry in inotify_device's list */
char *name; /* filename, if any */
};
/*
* struct inotify_watch - represents a watch request on a specific inode
*
* d_list is protected by dev->mutex of the associated watch->dev.
* i_list and mask are protected by inode->inotify_mutex of the associated inode.
* dev, inode, and wd are never written to once the watch is created.
*/
struct inotify_watch {
struct list_head d_list; /* entry in inotify_device's list */
struct list_head i_list; /* entry in inode's list */
atomic_t count; /* reference count */
struct inotify_device *dev; /* associated device */
struct inode *inode; /* associated inode */
s32 wd; /* watch descriptor */
u32 mask; /* event mask for this watch */
};
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int zero;
ctl_table inotify_table[] = {
{
.ctl_name = INOTIFY_MAX_USER_INSTANCES,
.procname = "max_user_instances",
.data = &inotify_max_user_instances,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &zero,
},
{
.ctl_name = INOTIFY_MAX_USER_WATCHES,
.procname = "max_user_watches",
.data = &inotify_max_user_watches,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &zero,
},
{
.ctl_name = INOTIFY_MAX_QUEUED_EVENTS,
.procname = "max_queued_events",
.data = &inotify_max_queued_events,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.strategy = &sysctl_intvec,
.extra1 = &zero
},
{ .ctl_name = 0 }
};
#endif /* CONFIG_SYSCTL */
static inline void get_inotify_dev(struct inotify_device *dev)
static inline void get_inotify_handle(struct inotify_handle *ih)
{
atomic_inc(&dev->count);
atomic_inc(&ih->count);
}
static inline void put_inotify_dev(struct inotify_device *dev)
static inline void put_inotify_handle(struct inotify_handle *ih)
{
if (atomic_dec_and_test(&dev->count)) {
atomic_dec(&dev->user->inotify_devs);
free_uid(dev->user);
idr_destroy(&dev->idr);
kfree(dev);
if (atomic_dec_and_test(&ih->count)) {
idr_destroy(&ih->idr);
kfree(ih);
}
}
static inline void get_inotify_watch(struct inotify_watch *watch)
/**
* get_inotify_watch - grab a reference to an inotify_watch
* @watch: watch to grab
*/
void get_inotify_watch(struct inotify_watch *watch)
{
atomic_inc(&watch->count);
}
EXPORT_SYMBOL_GPL(get_inotify_watch);
/*
/**
* put_inotify_watch - decrements the ref count on a given watch. cleans up
* the watch and its references if the count reaches zero.
* watch references if the count reaches zero. inotify_watch is freed by
* inotify callers via the destroy_watch() op.
* @watch: watch to release
*/
static inline void put_inotify_watch(struct inotify_watch *watch)
void put_inotify_watch(struct inotify_watch *watch)
{
if (atomic_dec_and_test(&watch->count)) {
put_inotify_dev(watch->dev);
iput(watch->inode);
kmem_cache_free(watch_cachep, watch);
}
}
/*
* kernel_event - create a new kernel event with the given parameters
*
* This function can sleep.
*/
static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie,
const char *name)
{
struct inotify_kernel_event *kevent;
kevent = kmem_cache_alloc(event_cachep, GFP_KERNEL);
if (unlikely(!kevent))
return NULL;
/* we hand this out to user-space, so zero it just in case */
memset(&kevent->event, 0, sizeof(struct inotify_event));
kevent->event.wd = wd;
kevent->event.mask = mask;
kevent->event.cookie = cookie;
INIT_LIST_HEAD(&kevent->list);
if (name) {
size_t len, rem, event_size = sizeof(struct inotify_event);
/*
* We need to pad the filename so as to properly align an
* array of inotify_event structures. Because the structure is
* small and the common case is a small filename, we just round
* up to the next multiple of the structure's sizeof. This is
* simple and safe for all architectures.
*/
len = strlen(name) + 1;
rem = event_size - len;
if (len > event_size) {
rem = event_size - (len % event_size);
if (len % event_size == 0)
rem = 0;
}
kevent->name = kmalloc(len + rem, GFP_KERNEL);
if (unlikely(!kevent->name)) {
kmem_cache_free(event_cachep, kevent);
return NULL;
}
memcpy(kevent->name, name, len);
if (rem)
memset(kevent->name + len, 0, rem);
kevent->event.len = len + rem;
} else {
kevent->event.len = 0;
kevent->name = NULL;
}
return kevent;
}
/*
* inotify_dev_get_event - return the next event in the given dev's queue
*
* Caller must hold dev->mutex.
*/
static inline struct inotify_kernel_event *
inotify_dev_get_event(struct inotify_device *dev)
{
return list_entry(dev->events.next, struct inotify_kernel_event, list);
}
/*
* inotify_dev_queue_event - add a new event to the given device
*
* Caller must hold dev->mutex. Can sleep (calls kernel_event()).
*/
static void inotify_dev_queue_event(struct inotify_device *dev,
struct inotify_watch *watch, u32 mask,
u32 cookie, const char *name)
{
struct inotify_kernel_event *kevent, *last;
/* coalescing: drop this event if it is a dupe of the previous */
last = inotify_dev_get_event(dev);
if (last && last->event.mask == mask && last->event.wd == watch->wd &&
last->event.cookie == cookie) {
const char *lastname = last->name;
if (!name && !lastname)
return;
if (name && lastname && !strcmp(lastname, name))
return;
}
/* the queue overflowed and we already sent the Q_OVERFLOW event */
if (unlikely(dev->event_count > dev->max_events))
return;
/* if the queue overflows, we need to notify user space */
if (unlikely(dev->event_count == dev->max_events))
kevent = kernel_event(-1, IN_Q_OVERFLOW, cookie, NULL);
else
kevent = kernel_event(watch->wd, mask, cookie, name);
if (unlikely(!kevent))
return;
/* queue the event and wake up anyone waiting */
dev->event_count++;
dev->queue_size += sizeof(struct inotify_event) + kevent->event.len;
list_add_tail(&kevent->list, &dev->events);
wake_up_interruptible(&dev->wq);
}
/*
* remove_kevent - cleans up and ultimately frees the given kevent
*
* Caller must hold dev->mutex.
*/
static void remove_kevent(struct inotify_device *dev,
struct inotify_kernel_event *kevent)
{
list_del(&kevent->list);
struct inotify_handle *ih = watch->ih;
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->mutex.
*/
static void inotify_dev_event_dequeue(struct inotify_device *dev)
{
if (!list_empty(&dev->events)) {
struct inotify_kernel_event *kevent;
kevent = inotify_dev_get_event(dev);
remove_kevent(dev, kevent);
iput(watch->inode);
ih->in_ops->destroy_watch(watch);
put_inotify_handle(ih);
}
}
EXPORT_SYMBOL_GPL(put_inotify_watch);
/*
* inotify_dev_get_wd - returns the next WD for use by the given dev
* inotify_handle_get_wd - returns the next WD for use by the given handle
*
* Callers must hold dev->mutex. This function can sleep.
* Callers must hold ih->mutex. This function can sleep.
*/
static int inotify_dev_get_wd(struct inotify_device *dev,
struct inotify_watch *watch)
static int inotify_handle_get_wd(struct inotify_handle *ih,
struct inotify_watch *watch)
{
int ret;
do {
if (unlikely(!idr_pre_get(&dev->idr, GFP_KERNEL)))
if (unlikely(!idr_pre_get(&ih->idr, GFP_KERNEL)))
return -ENOSPC;
ret = idr_get_new_above(&dev->idr, watch, dev->last_wd+1, &watch->wd);
ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
} while (ret == -EAGAIN);
return ret;
}
if (likely(!ret))
ih->last_wd = watch->wd;
/*
* find_inode - resolve a user-given path to a specific inode and return a nd
*/
static int find_inode(const char __user *dirname, struct nameidata *nd,
unsigned flags)
{
int error;
error = __user_walk(dirname, flags, nd);
if (error)
return error;
/* you can only watch an inode if you have read permissions on it */
error = vfs_permission(nd, MAY_READ);
if (error)
path_release(nd);
return error;
return ret;
}
/*
......@@ -422,67 +188,18 @@ static void set_dentry_child_flags(struct inode *inode, int watched)
}
/*
* create_watch - creates a watch on the given device.
*
* Callers must hold dev->mutex. Calls inotify_dev_get_wd() so may sleep.
* Both 'dev' and 'inode' (by way of nameidata) need to be pinned.
*/
static struct inotify_watch *create_watch(struct inotify_device *dev,
u32 mask, struct inode *inode)
{
struct inotify_watch *watch;
int ret;
if (atomic_read(&dev->user->inotify_watches) >=
inotify_max_user_watches)
return ERR_PTR(-ENOSPC);
watch = kmem_cache_alloc(watch_cachep, GFP_KERNEL);
if (unlikely(!watch))
return ERR_PTR(-ENOMEM);
ret = inotify_dev_get_wd(dev, watch);
if (unlikely(ret)) {
kmem_cache_free(watch_cachep, watch);
return ERR_PTR(ret);
}
dev->last_wd = watch->wd;
watch->mask = mask;
atomic_set(&watch->count, 0);
INIT_LIST_HEAD(&watch->d_list);
INIT_LIST_HEAD(&watch->i_list);
/* save a reference to device and bump the count to make it official */
get_inotify_dev(dev);
watch->dev = dev;
/*
* Save a reference to the inode and bump the ref count to make it
* official. We hold a reference to nameidata, which makes this safe.
*/
watch->inode = igrab(inode);
/* bump our own count, corresponding to our entry in dev->watches */
get_inotify_watch(watch);
atomic_inc(&dev->user->inotify_watches);
return watch;
}
/*
* inotify_find_dev - find the watch associated with the given inode and dev
* inotify_find_handle - find the watch associated with the given inode and
* handle
*
* Callers must hold inode->inotify_mutex.
*/
static struct inotify_watch *inode_find_dev(struct inode *inode,
struct inotify_device *dev)
static struct inotify_watch *inode_find_handle(struct inode *inode,
struct inotify_handle *ih)
{
struct inotify_watch *watch;
list_for_each_entry(watch, &inode->inotify_watches, i_list) {
if (watch->dev == dev)
if (watch->ih == ih)
return watch;
}
......@@ -491,39 +208,34 @@ static struct inotify_watch *inode_find_dev(struct inode *inode,
/*
* remove_watch_no_event - remove_watch() without the IN_IGNORED event.
*
* Callers must hold both inode->inotify_mutex and ih->mutex.
*/
static void remove_watch_no_event(struct inotify_watch *watch,
struct inotify_device *dev)
struct inotify_handle *ih)
{
list_del(&watch->i_list);
list_del(&watch->d_list);
list_del(&watch->h_list);
if (!inotify_inode_watched(watch->inode))
set_dentry_child_flags(watch->inode, 0);
atomic_dec(&dev->user->inotify_watches);
idr_remove(&dev->idr, watch->wd);
put_inotify_watch(watch);
idr_remove(&ih->idr, watch->wd);
}
/*
* remove_watch - Remove a watch from both the device and the inode. Sends
* the IN_IGNORED event to the given device signifying that the inode is no
* longer watched.
*
* Callers must hold both inode->inotify_mutex and dev->mutex. We drop a
* reference to the inode before returning.
* remove_watch - Remove a watch from both the handle and the inode. Sends
* the IN_IGNORED event signifying that the inode is no longer watched.
*
* The inode is not iput() so as to remain atomic. If the inode needs to be
* iput(), the call returns one. Otherwise, it returns zero.
* Callers must hold both inode->inotify_mutex and ih->mutex.
*/
static void remove_watch(struct inotify_watch *watch,struct inotify_device *dev)
static void remove_watch(struct inotify_watch *watch, struct inotify_handle *ih)
{
inotify_dev_queue_event(dev, watch, IN_IGNORED, 0, NULL);
remove_watch_no_event(watch, dev);
remove_watch_no_event(watch, ih);
ih->in_ops->handle_event(watch, watch->wd, IN_IGNORED, 0, NULL);
}
/* Kernel API */
/* Kernel API for producing events */
/*
* inotify_d_instantiate - instantiate dcache entry for inode
......@@ -576,14 +288,12 @@ void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
u32 watch_mask = watch->mask;
if (watch_mask & mask) {
struct inotify_device *dev = watch->dev;
get_inotify_watch(watch);
mutex_lock(&dev->mutex);
inotify_dev_queue_event(dev, watch, mask, cookie, name);
struct inotify_handle *ih= watch->ih;
mutex_lock(&ih->mutex);
if (watch_mask & IN_ONESHOT)
remove_watch_no_event(watch, dev);
mutex_unlock(&dev->mutex);
put_inotify_watch(watch);
remove_watch_no_event(watch, ih);
ih->in_ops->handle_event(watch, watch->wd, mask, cookie, name);
mutex_unlock(&ih->mutex);
}
}
mutex_unlock(&inode->inotify_mutex);
......@@ -694,11 +404,12 @@ void inotify_unmount_inodes(struct list_head *list)
mutex_lock(&inode->inotify_mutex);
watches = &inode->inotify_watches;
list_for_each_entry_safe(watch, next_w, watches, i_list) {
struct inotify_device *dev = watch->dev;
mutex_lock(&dev->mutex);
inotify_dev_queue_event(dev, watch, IN_UNMOUNT,0,NULL);