2006-06-02 04:10:59 +08:00
|
|
|
/*
|
|
|
|
* fs/inotify_user.c - inotify support for userspace
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* John McCutchan <ttb@tentacle.dhs.org>
|
|
|
|
* Robert Love <rml@novell.com>
|
|
|
|
*
|
|
|
|
* Copyright (C) 2005 John McCutchan
|
|
|
|
* Copyright 2006 Hewlett-Packard Development Company, L.P.
|
|
|
|
*
|
2009-05-22 05:02:01 +08:00
|
|
|
* Copyright (C) 2009 Eric Paris <Red Hat Inc>
|
|
|
|
* inotify was largely rewriten to make use of the fsnotify infrastructure
|
|
|
|
*
|
2006-06-02 04:10:59 +08:00
|
|
|
* 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/file.h>
|
2009-05-22 05:02:01 +08:00
|
|
|
#include <linux/fs.h> /* struct inode */
|
|
|
|
#include <linux/fsnotify_backend.h>
|
|
|
|
#include <linux/idr.h>
|
|
|
|
#include <linux/init.h> /* module_init */
|
2006-06-02 04:10:59 +08:00
|
|
|
#include <linux/inotify.h>
|
2009-05-22 05:02:01 +08:00
|
|
|
#include <linux/kernel.h> /* roundup() */
|
|
|
|
#include <linux/magic.h> /* superblock magic number */
|
|
|
|
#include <linux/mount.h> /* mntget */
|
|
|
|
#include <linux/namei.h> /* LOOKUP_FOLLOW */
|
|
|
|
#include <linux/path.h> /* struct path */
|
|
|
|
#include <linux/sched.h> /* struct user */
|
|
|
|
#include <linux/slab.h> /* struct kmem_cache */
|
2006-06-02 04:10:59 +08:00
|
|
|
#include <linux/syscalls.h>
|
2009-05-22 05:02:01 +08:00
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <linux/wait.h>
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
#include "inotify.h"
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
#include <asm/ioctls.h>
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
static struct vfsmount *inotify_mnt __read_mostly;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* this just sits here and wastes global memory. used to just pad userspace messages with zeros */
|
|
|
|
static struct inotify_event nul_inotify_event;
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
/* these are configurable via /proc/sys/fs/inotify/ */
|
2008-02-15 11:31:21 +08:00
|
|
|
static int inotify_max_user_instances __read_mostly;
|
|
|
|
static int inotify_max_queued_events __read_mostly;
|
2009-05-22 05:02:01 +08:00
|
|
|
int inotify_max_user_watches __read_mostly;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
|
|
|
|
struct kmem_cache *event_priv_cachep __read_mostly;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
/*
|
2009-05-22 05:02:01 +08:00
|
|
|
* When inotify registers a new group it increments this and uses that
|
|
|
|
* value as an offset to set the fsnotify group "name" and priority.
|
2006-06-02 04:10:59 +08:00
|
|
|
*/
|
2009-05-22 05:02:01 +08:00
|
|
|
static atomic_t inotify_grp_num;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
#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 */
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
static inline __u32 inotify_arg_to_mask(u32 arg)
|
2008-02-06 17:36:09 +08:00
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
__u32 mask;
|
2008-02-06 17:36:09 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* everything should accept their own ignored and cares about children */
|
|
|
|
mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* mask off the flags used to open the fd */
|
|
|
|
mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT));
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
return mask;
|
2006-06-02 04:10:59 +08:00
|
|
|
}
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
static inline u32 inotify_mask_to_arg(__u32 mask)
|
2006-06-02 04:10:59 +08:00
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
|
|
|
|
IN_Q_OVERFLOW);
|
2006-06-02 04:10:59 +08:00
|
|
|
}
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* intofiy userspace file descriptor functions */
|
2006-06-02 04:10:59 +08:00
|
|
|
static unsigned int inotify_poll(struct file *file, poll_table *wait)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group = file->private_data;
|
2006-06-02 04:10:59 +08:00
|
|
|
int ret = 0;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
poll_wait(file, &group->notification_waitq, wait);
|
|
|
|
mutex_lock(&group->notification_mutex);
|
|
|
|
if (!fsnotify_notify_queue_is_empty(group))
|
2006-06-02 04:10:59 +08:00
|
|
|
ret = POLLIN | POLLRDNORM;
|
2009-05-22 05:02:01 +08:00
|
|
|
mutex_unlock(&group->notification_mutex);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
/*
|
|
|
|
* Get an inotify_kernel_event if one exists and is small
|
|
|
|
* enough to fit in "count". Return an error pointer if
|
|
|
|
* not large enough.
|
|
|
|
*
|
2009-05-22 05:02:01 +08:00
|
|
|
* Called with the group->notification_mutex held.
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
*/
|
2009-05-22 05:02:01 +08:00
|
|
|
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
|
|
|
|
size_t count)
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
{
|
|
|
|
size_t event_size = sizeof(struct inotify_event);
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_event *event;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
if (fsnotify_notify_queue_is_empty(group))
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
return NULL;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
event = fsnotify_peek_notify_event(group);
|
|
|
|
|
|
|
|
event_size += roundup(event->name_len, event_size);
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
|
|
|
|
if (event_size > count)
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* held the notification_mutex the whole time, so this is the
|
|
|
|
* same event we peeked above */
|
|
|
|
fsnotify_remove_notify_event(group);
|
|
|
|
|
|
|
|
return event;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy an event to user space, returning how much we copied.
|
|
|
|
*
|
|
|
|
* We already checked that the event size is smaller than the
|
|
|
|
* buffer we had in "get_one_event()" above.
|
|
|
|
*/
|
2009-05-22 05:02:01 +08:00
|
|
|
static ssize_t copy_event_to_user(struct fsnotify_group *group,
|
|
|
|
struct fsnotify_event *event,
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
char __user *buf)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct inotify_event inotify_event;
|
|
|
|
struct fsnotify_event_private_data *fsn_priv;
|
|
|
|
struct inotify_event_private_data *priv;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
size_t event_size = sizeof(struct inotify_event);
|
2009-05-22 05:02:01 +08:00
|
|
|
size_t name_len;
|
|
|
|
|
|
|
|
/* we get the inotify watch descriptor from the event private data */
|
|
|
|
spin_lock(&event->lock);
|
|
|
|
fsn_priv = fsnotify_remove_priv_from_event(group, event);
|
|
|
|
spin_unlock(&event->lock);
|
|
|
|
|
|
|
|
if (!fsn_priv)
|
|
|
|
inotify_event.wd = -1;
|
|
|
|
else {
|
|
|
|
priv = container_of(fsn_priv, struct inotify_event_private_data,
|
|
|
|
fsnotify_event_priv_data);
|
|
|
|
inotify_event.wd = priv->wd;
|
|
|
|
inotify_free_event_priv(fsn_priv);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* round up event->name_len so it is a multiple of event_size */
|
|
|
|
name_len = roundup(event->name_len, event_size);
|
|
|
|
inotify_event.len = name_len;
|
|
|
|
|
|
|
|
inotify_event.mask = inotify_mask_to_arg(event->mask);
|
|
|
|
inotify_event.cookie = event->sync_cookie;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* send the main event */
|
|
|
|
if (copy_to_user(buf, &inotify_event, event_size))
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
return -EFAULT;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
buf += event_size;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/*
|
|
|
|
* fsnotify only stores the pathname, so here we have to send the pathname
|
|
|
|
* and then pad that pathname out to a multiple of sizeof(inotify_event)
|
|
|
|
* with zeros. I get my zeros from the nul_inotify_event.
|
|
|
|
*/
|
|
|
|
if (name_len) {
|
|
|
|
unsigned int len_to_zero = name_len - event->name_len;
|
|
|
|
/* copy the path name */
|
|
|
|
if (copy_to_user(buf, event->file_name, event->name_len))
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
return -EFAULT;
|
2009-05-22 05:02:01 +08:00
|
|
|
buf += event->name_len;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* fill userspace with 0's from nul_inotify_event */
|
|
|
|
if (copy_to_user(buf, &nul_inotify_event, len_to_zero))
|
|
|
|
return -EFAULT;
|
|
|
|
buf += len_to_zero;
|
|
|
|
event_size += name_len;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
}
|
2009-05-22 05:02:01 +08:00
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
return event_size;
|
|
|
|
}
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
static ssize_t inotify_read(struct file *file, char __user *buf,
|
|
|
|
size_t count, loff_t *pos)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group;
|
|
|
|
struct fsnotify_event *kevent;
|
2006-06-02 04:10:59 +08:00
|
|
|
char __user *start;
|
|
|
|
int ret;
|
|
|
|
DEFINE_WAIT(wait);
|
|
|
|
|
|
|
|
start = buf;
|
2009-05-22 05:02:01 +08:00
|
|
|
group = file->private_data;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
while (1) {
|
2009-05-22 05:02:01 +08:00
|
|
|
prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
mutex_lock(&group->notification_mutex);
|
|
|
|
kevent = get_one_event(group, count);
|
|
|
|
mutex_unlock(&group->notification_mutex);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
if (kevent) {
|
|
|
|
ret = PTR_ERR(kevent);
|
|
|
|
if (IS_ERR(kevent))
|
|
|
|
break;
|
2009-05-22 05:02:01 +08:00
|
|
|
ret = copy_event_to_user(group, kevent, buf);
|
|
|
|
fsnotify_put_event(kevent);
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
if (ret < 0)
|
|
|
|
break;
|
|
|
|
buf += ret;
|
|
|
|
count -= ret;
|
|
|
|
continue;
|
2006-06-02 04:10:59 +08:00
|
|
|
}
|
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
ret = -EAGAIN;
|
|
|
|
if (file->f_flags & O_NONBLOCK)
|
2006-06-02 04:10:59 +08:00
|
|
|
break;
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
ret = -EINTR;
|
|
|
|
if (signal_pending(current))
|
2006-06-02 04:10:59 +08:00
|
|
|
break;
|
2008-10-03 05:50:12 +08:00
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
if (start != buf)
|
2006-06-02 04:10:59 +08:00
|
|
|
break;
|
2008-10-03 05:50:12 +08:00
|
|
|
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
schedule();
|
2006-06-02 04:10:59 +08:00
|
|
|
}
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
finish_wait(&group->notification_waitq, &wait);
|
inotify: clean up inotify_read and fix locking problems
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-22 22:29:45 +08:00
|
|
|
if (start != buf && ret != -EFAULT)
|
|
|
|
ret = buf - start;
|
2006-06-02 04:10:59 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2008-02-06 17:36:19 +08:00
|
|
|
static int inotify_fasync(int fd, struct file *file, int on)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group = file->private_data;
|
2008-02-06 17:36:19 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
return fasync_helper(fd, file, on, &group->inotify_data.fa) >= 0 ? 0 : -EIO;
|
2008-02-06 17:36:19 +08:00
|
|
|
}
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
static int inotify_release(struct inode *ignored, struct file *file)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group = file->private_data;
|
2009-07-02 12:56:38 +08:00
|
|
|
struct user_struct *user = group->inotify_data.user;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
fsnotify_clear_marks_by_group(group);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* free this group, matching get was inotify_init->fsnotify_obtain_group */
|
|
|
|
fsnotify_put_group(group);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-07-02 12:56:38 +08:00
|
|
|
atomic_dec(&user->inotify_devs);
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static long inotify_ioctl(struct file *file, unsigned int cmd,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group;
|
|
|
|
struct fsnotify_event_holder *holder;
|
|
|
|
struct fsnotify_event *event;
|
2006-06-02 04:10:59 +08:00
|
|
|
void __user *p;
|
|
|
|
int ret = -ENOTTY;
|
2009-05-22 05:02:01 +08:00
|
|
|
size_t send_len = 0;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
group = file->private_data;
|
2006-06-02 04:10:59 +08:00
|
|
|
p = (void __user *) arg;
|
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
case FIONREAD:
|
2009-05-22 05:02:01 +08:00
|
|
|
mutex_lock(&group->notification_mutex);
|
|
|
|
list_for_each_entry(holder, &group->notification_list, event_list) {
|
|
|
|
event = holder->event;
|
|
|
|
send_len += sizeof(struct inotify_event);
|
|
|
|
send_len += roundup(event->name_len,
|
|
|
|
sizeof(struct inotify_event));
|
|
|
|
}
|
|
|
|
mutex_unlock(&group->notification_mutex);
|
|
|
|
ret = put_user(send_len, (int __user *) p);
|
2006-06-02 04:10:59 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations inotify_fops = {
|
2009-05-22 05:02:01 +08:00
|
|
|
.poll = inotify_poll,
|
|
|
|
.read = inotify_read,
|
|
|
|
.fasync = inotify_fasync,
|
|
|
|
.release = inotify_release,
|
|
|
|
.unlocked_ioctl = inotify_ioctl,
|
2006-06-02 04:10:59 +08:00
|
|
|
.compat_ioctl = inotify_ioctl,
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/*
|
|
|
|
* find_inode - resolve a user-given path to a specific inode
|
|
|
|
*/
|
|
|
|
static int inotify_find_inode(const char __user *dirname, struct path *path, unsigned flags)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
|
|
|
|
error = user_path_at(AT_FDCWD, dirname, flags, path);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
/* you can only watch an inode if you have read permissions on it */
|
|
|
|
error = inode_permission(path->dentry->d_inode, MAY_READ);
|
|
|
|
if (error)
|
|
|
|
path_put(path);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
/*
|
|
|
|
* Remove the mark from the idr (if present) and drop the reference
|
|
|
|
* on the mark because it was in the idr.
|
|
|
|
*/
|
2009-07-07 22:28:24 +08:00
|
|
|
static void inotify_remove_from_idr(struct fsnotify_group *group,
|
|
|
|
struct inotify_inode_mark_entry *ientry)
|
|
|
|
{
|
|
|
|
struct idr *idr;
|
2009-08-25 04:03:35 +08:00
|
|
|
struct fsnotify_mark_entry *entry;
|
|
|
|
struct inotify_inode_mark_entry *found_ientry;
|
|
|
|
int wd;
|
2009-07-07 22:28:24 +08:00
|
|
|
|
|
|
|
spin_lock(&group->inotify_data.idr_lock);
|
|
|
|
idr = &group->inotify_data.idr;
|
2009-08-25 04:03:35 +08:00
|
|
|
wd = ientry->wd;
|
|
|
|
|
|
|
|
if (wd == -1)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
entry = idr_find(&group->inotify_data.idr, wd);
|
|
|
|
if (unlikely(!entry))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
found_ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
|
|
|
|
if (unlikely(found_ientry != ientry)) {
|
|
|
|
/* We found an entry in the idr with the right wd, but it's
|
|
|
|
* not the entry we were told to remove. eparis seriously
|
|
|
|
* fucked up somewhere. */
|
|
|
|
WARN_ON(1);
|
|
|
|
ientry->wd = -1;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* One ref for being in the idr, one ref held by the caller */
|
|
|
|
BUG_ON(atomic_read(&entry->refcnt) < 2);
|
|
|
|
|
|
|
|
idr_remove(idr, wd);
|
2009-07-07 22:28:24 +08:00
|
|
|
ientry->wd = -1;
|
2009-08-25 04:03:35 +08:00
|
|
|
|
|
|
|
/* removed from the idr, drop that ref */
|
|
|
|
fsnotify_put_mark(entry);
|
|
|
|
out:
|
|
|
|
spin_unlock(&group->inotify_data.idr_lock);
|
2009-07-07 22:28:24 +08:00
|
|
|
}
|
2009-08-25 04:03:35 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/*
|
2009-08-25 04:03:35 +08:00
|
|
|
* Send IN_IGNORED for this wd, remove this wd from the idr.
|
2009-05-22 05:02:01 +08:00
|
|
|
*/
|
2009-06-13 04:04:26 +08:00
|
|
|
void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
|
|
|
|
struct fsnotify_group *group)
|
2009-05-22 05:02:01 +08:00
|
|
|
{
|
|
|
|
struct inotify_inode_mark_entry *ientry;
|
2009-07-16 03:49:52 +08:00
|
|
|
struct fsnotify_event *ignored_event;
|
2009-05-22 05:02:01 +08:00
|
|
|
struct inotify_event_private_data *event_priv;
|
|
|
|
struct fsnotify_event_private_data *fsn_event_priv;
|
2009-08-17 09:51:44 +08:00
|
|
|
int ret;
|
2009-05-22 05:02:01 +08:00
|
|
|
|
2009-07-16 03:49:52 +08:00
|
|
|
ignored_event = fsnotify_create_event(NULL, FS_IN_IGNORED, NULL,
|
|
|
|
FSNOTIFY_EVENT_NONE, NULL, 0,
|
|
|
|
GFP_NOFS);
|
|
|
|
if (!ignored_event)
|
|
|
|
return;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
|
|
|
|
|
2009-07-16 03:49:52 +08:00
|
|
|
event_priv = kmem_cache_alloc(event_priv_cachep, GFP_NOFS);
|
2009-05-22 05:02:01 +08:00
|
|
|
if (unlikely(!event_priv))
|
|
|
|
goto skip_send_ignore;
|
|
|
|
|
|
|
|
fsn_event_priv = &event_priv->fsnotify_event_priv_data;
|
|
|
|
|
|
|
|
fsn_event_priv->group = group;
|
|
|
|
event_priv->wd = ientry->wd;
|
|
|
|
|
2009-08-17 09:51:44 +08:00
|
|
|
ret = fsnotify_add_notify_event(group, ignored_event, fsn_event_priv);
|
|
|
|
if (ret)
|
2009-05-22 05:02:01 +08:00
|
|
|
inotify_free_event_priv(fsn_event_priv);
|
|
|
|
|
|
|
|
skip_send_ignore:
|
|
|
|
|
2009-07-16 03:49:52 +08:00
|
|
|
/* matches the reference taken when the event was created */
|
|
|
|
fsnotify_put_event(ignored_event);
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* remove this entry from the idr */
|
2009-07-07 22:28:24 +08:00
|
|
|
inotify_remove_from_idr(group, ientry);
|
2009-05-22 05:02:01 +08:00
|
|
|
|
2009-07-07 22:28:23 +08:00
|
|
|
atomic_dec(&group->inotify_data.user->inotify_watches);
|
2009-05-22 05:02:01 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ding dong the mark is dead */
|
|
|
|
static void inotify_free_mark(struct fsnotify_mark_entry *entry)
|
|
|
|
{
|
|
|
|
struct inotify_inode_mark_entry *ientry = (struct inotify_inode_mark_entry *)entry;
|
|
|
|
|
|
|
|
kmem_cache_free(inotify_inode_mark_cachep, ientry);
|
|
|
|
}
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
static int inotify_update_existing_watch(struct fsnotify_group *group,
|
|
|
|
struct inode *inode,
|
|
|
|
u32 arg)
|
2009-05-22 05:02:01 +08:00
|
|
|
{
|
2009-08-25 04:03:35 +08:00
|
|
|
struct fsnotify_mark_entry *entry;
|
2009-05-22 05:02:01 +08:00
|
|
|
struct inotify_inode_mark_entry *ientry;
|
|
|
|
__u32 old_mask, new_mask;
|
2009-08-25 04:03:35 +08:00
|
|
|
__u32 mask;
|
|
|
|
int add = (arg & IN_MASK_ADD);
|
|
|
|
int ret;
|
2009-05-22 05:02:01 +08:00
|
|
|
|
|
|
|
/* don't allow invalid bits: we don't want flags set */
|
|
|
|
mask = inotify_arg_to_mask(arg);
|
|
|
|
if (unlikely(!mask))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
spin_lock(&inode->i_lock);
|
|
|
|
entry = fsnotify_find_mark_entry(group, inode);
|
|
|
|
spin_unlock(&inode->i_lock);
|
2009-08-25 04:03:35 +08:00
|
|
|
if (!entry)
|
|
|
|
return -ENOENT;
|
2009-07-07 22:28:24 +08:00
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
|
2009-07-07 22:28:23 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
spin_lock(&entry->lock);
|
|
|
|
|
|
|
|
old_mask = entry->mask;
|
|
|
|
if (add) {
|
|
|
|
entry->mask |= mask;
|
|
|
|
new_mask = entry->mask;
|
|
|
|
} else {
|
|
|
|
entry->mask = mask;
|
|
|
|
new_mask = entry->mask;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_unlock(&entry->lock);
|
|
|
|
|
|
|
|
if (old_mask != new_mask) {
|
|
|
|
/* more bits in old than in new? */
|
|
|
|
int dropped = (old_mask & ~new_mask);
|
|
|
|
/* more bits in this entry than the inode's mask? */
|
|
|
|
int do_inode = (new_mask & ~inode->i_fsnotify_mask);
|
|
|
|
/* more bits in this entry than the group? */
|
|
|
|
int do_group = (new_mask & ~group->mask);
|
|
|
|
|
|
|
|
/* update the inode with this new entry */
|
|
|
|
if (dropped || do_inode)
|
|
|
|
fsnotify_recalc_inode_mask(inode);
|
|
|
|
|
|
|
|
/* update the group mask with the new mask */
|
|
|
|
if (dropped || do_group)
|
|
|
|
fsnotify_recalc_group_mask(group);
|
|
|
|
}
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
/* return the wd */
|
|
|
|
ret = ientry->wd;
|
|
|
|
|
|
|
|
/* match the get from fsnotify_find_mark_entry() */
|
2009-07-07 22:28:23 +08:00
|
|
|
fsnotify_put_mark(entry);
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int inotify_new_watch(struct fsnotify_group *group,
|
|
|
|
struct inode *inode,
|
|
|
|
u32 arg)
|
|
|
|
{
|
|
|
|
struct inotify_inode_mark_entry *tmp_ientry;
|
|
|
|
__u32 mask;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/* don't allow invalid bits: we don't want flags set */
|
|
|
|
mask = inotify_arg_to_mask(arg);
|
|
|
|
if (unlikely(!mask))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
|
|
|
|
if (unlikely(!tmp_ientry))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
|
|
|
|
tmp_ientry->fsn_entry.mask = mask;
|
|
|
|
tmp_ientry->wd = -1;
|
|
|
|
|
|
|
|
ret = -ENOSPC;
|
|
|
|
if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
|
|
|
|
goto out_err;
|
|
|
|
retry:
|
|
|
|
ret = -ENOMEM;
|
|
|
|
if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
|
|
|
|
goto out_err;
|
|
|
|
|
|
|
|
spin_lock(&group->inotify_data.idr_lock);
|
|
|
|
ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
|
|
|
|
group->inotify_data.last_wd,
|
|
|
|
&tmp_ientry->wd);
|
|
|
|
spin_unlock(&group->inotify_data.idr_lock);
|
|
|
|
if (ret) {
|
|
|
|
/* idr was out of memory allocate and try again */
|
|
|
|
if (ret == -EAGAIN)
|
|
|
|
goto retry;
|
|
|
|
goto out_err;
|
|
|
|
}
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
/* we put the mark on the idr, take a reference */
|
|
|
|
fsnotify_get_mark(&tmp_ientry->fsn_entry);
|
|
|
|
|
2009-08-25 04:03:35 +08:00
|
|
|
/* we are on the idr, now get on the inode */
|
|
|
|
ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
|
|
|
|
if (ret) {
|
|
|
|
/* we failed to get on the inode, get off the idr */
|
|
|
|
inotify_remove_from_idr(group, tmp_ientry);
|
|
|
|
goto out_err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* update the idr hint, who cares about races, it's just a hint */
|
|
|
|
group->inotify_data.last_wd = tmp_ientry->wd;
|
|
|
|
|
|
|
|
/* increment the number of watches the user has */
|
|
|
|
atomic_inc(&group->inotify_data.user->inotify_watches);
|
|
|
|
|
|
|
|
/* return the watch descriptor for this new entry */
|
|
|
|
ret = tmp_ientry->wd;
|
|
|
|
|
|
|
|
/* match the ref from fsnotify_init_markentry() */
|
|
|
|
fsnotify_put_mark(&tmp_ientry->fsn_entry);
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
out_err:
|
2009-08-25 04:03:35 +08:00
|
|
|
if (ret < 0)
|
2009-07-07 22:28:24 +08:00
|
|
|
kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
|
2009-08-25 04:03:35 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
retry:
|
|
|
|
/* try to update and existing watch with the new arg */
|
|
|
|
ret = inotify_update_existing_watch(group, inode, arg);
|
|
|
|
/* no mark present, try to add a new one */
|
|
|
|
if (ret == -ENOENT)
|
|
|
|
ret = inotify_new_watch(group, inode, arg);
|
|
|
|
/*
|
|
|
|
* inotify_new_watch could race with another thread which did an
|
|
|
|
* inotify_new_watch between the update_existing and the add watch
|
|
|
|
* here, go back and try to update an existing mark again.
|
|
|
|
*/
|
|
|
|
if (ret == -EEXIST)
|
|
|
|
goto retry;
|
2009-07-07 22:28:24 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsigned int max_events)
|
|
|
|
{
|
|
|
|
struct fsnotify_group *group;
|
|
|
|
unsigned int grp_num;
|
|
|
|
|
|
|
|
/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
|
|
|
|
grp_num = (INOTIFY_GROUP_NUM - atomic_inc_return(&inotify_grp_num));
|
|
|
|
group = fsnotify_obtain_group(grp_num, 0, &inotify_fsnotify_ops);
|
|
|
|
if (IS_ERR(group))
|
|
|
|
return group;
|
|
|
|
|
|
|
|
group->max_events = max_events;
|
|
|
|
|
|
|
|
spin_lock_init(&group->inotify_data.idr_lock);
|
|
|
|
idr_init(&group->inotify_data.idr);
|
2009-08-17 09:51:55 +08:00
|
|
|
group->inotify_data.last_wd = 1;
|
2009-05-22 05:02:01 +08:00
|
|
|
group->inotify_data.user = user;
|
|
|
|
group->inotify_data.fa = NULL;
|
|
|
|
|
|
|
|
return group;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* inotify syscalls */
|
2009-01-14 21:14:30 +08:00
|
|
|
SYSCALL_DEFINE1(inotify_init1, int, flags)
|
2006-06-02 04:10:59 +08:00
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group;
|
2006-06-02 04:10:59 +08:00
|
|
|
struct user_struct *user;
|
|
|
|
struct file *filp;
|
|
|
|
int fd, ret;
|
|
|
|
|
2008-07-24 12:29:42 +08:00
|
|
|
/* Check the IN_* constants for consistency. */
|
|
|
|
BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
|
|
|
|
BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
|
|
|
|
|
2008-07-24 12:29:41 +08:00
|
|
|
if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
|
2008-07-24 12:29:32 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
fd = get_unused_fd_flags(flags & O_CLOEXEC);
|
2006-06-02 04:10:59 +08:00
|
|
|
if (fd < 0)
|
|
|
|
return fd;
|
|
|
|
|
|
|
|
filp = get_empty_filp();
|
|
|
|
if (!filp) {
|
|
|
|
ret = -ENFILE;
|
|
|
|
goto out_put_fd;
|
|
|
|
}
|
|
|
|
|
2008-11-14 07:39:05 +08:00
|
|
|
user = get_current_user();
|
2006-06-02 04:10:59 +08:00
|
|
|
if (unlikely(atomic_read(&user->inotify_devs) >=
|
|
|
|
inotify_max_user_instances)) {
|
|
|
|
ret = -EMFILE;
|
|
|
|
goto out_free_uid;
|
|
|
|
}
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
|
|
|
|
group = inotify_new_group(user, inotify_max_queued_events);
|
|
|
|
if (IS_ERR(group)) {
|
|
|
|
ret = PTR_ERR(group);
|
2006-06-02 04:10:59 +08:00
|
|
|
goto out_free_uid;
|
|
|
|
}
|
|
|
|
|
|
|
|
filp->f_op = &inotify_fops;
|
2006-12-08 18:36:35 +08:00
|
|
|
filp->f_path.mnt = mntget(inotify_mnt);
|
|
|
|
filp->f_path.dentry = dget(inotify_mnt->mnt_root);
|
|
|
|
filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
|
2006-06-02 04:10:59 +08:00
|
|
|
filp->f_mode = FMODE_READ;
|
2008-07-24 12:29:41 +08:00
|
|
|
filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
|
2009-05-22 05:02:01 +08:00
|
|
|
filp->private_data = group;
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
atomic_inc(&user->inotify_devs);
|
2009-05-22 05:02:01 +08:00
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
fd_install(fd, filp);
|
|
|
|
|
|
|
|
return fd;
|
2009-05-22 05:02:01 +08:00
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
out_free_uid:
|
|
|
|
free_uid(user);
|
|
|
|
put_filp(filp);
|
|
|
|
out_put_fd:
|
|
|
|
put_unused_fd(fd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-01-14 21:14:30 +08:00
|
|
|
SYSCALL_DEFINE0(inotify_init)
|
2008-07-24 12:29:32 +08:00
|
|
|
{
|
|
|
|
return sys_inotify_init1(0);
|
|
|
|
}
|
|
|
|
|
2009-01-14 21:14:31 +08:00
|
|
|
SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
|
|
|
|
u32, mask)
|
2006-06-02 04:10:59 +08:00
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group;
|
2006-06-02 04:10:59 +08:00
|
|
|
struct inode *inode;
|
2008-07-22 21:59:21 +08:00
|
|
|
struct path path;
|
2006-06-02 04:10:59 +08:00
|
|
|
struct file *filp;
|
|
|
|
int ret, fput_needed;
|
|
|
|
unsigned flags = 0;
|
|
|
|
|
|
|
|
filp = fget_light(fd, &fput_needed);
|
|
|
|
if (unlikely(!filp))
|
|
|
|
return -EBADF;
|
|
|
|
|
|
|
|
/* verify that this is indeed an inotify instance */
|
|
|
|
if (unlikely(filp->f_op != &inotify_fops)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fput_and_out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(mask & IN_DONT_FOLLOW))
|
|
|
|
flags |= LOOKUP_FOLLOW;
|
|
|
|
if (mask & IN_ONLYDIR)
|
|
|
|
flags |= LOOKUP_DIRECTORY;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
ret = inotify_find_inode(pathname, &path, flags);
|
|
|
|
if (ret)
|
2006-06-02 04:10:59 +08:00
|
|
|
goto fput_and_out;
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* inode held in place by reference to path; group by fget on fd */
|
2008-07-22 21:59:21 +08:00
|
|
|
inode = path.dentry->d_inode;
|
2009-05-22 05:02:01 +08:00
|
|
|
group = filp->private_data;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
/* create/update an inode mark */
|
|
|
|
ret = inotify_update_watch(group, inode, mask);
|
|
|
|
if (unlikely(ret))
|
|
|
|
goto path_put_and_out;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
path_put_and_out:
|
2008-07-22 21:59:21 +08:00
|
|
|
path_put(&path);
|
2006-06-02 04:10:59 +08:00
|
|
|
fput_and_out:
|
|
|
|
fput_light(filp, fput_needed);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-01-14 21:14:31 +08:00
|
|
|
SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
|
2006-06-02 04:10:59 +08:00
|
|
|
{
|
2009-05-22 05:02:01 +08:00
|
|
|
struct fsnotify_group *group;
|
|
|
|
struct fsnotify_mark_entry *entry;
|
2006-06-02 04:10:59 +08:00
|
|
|
struct file *filp;
|
2009-05-22 05:02:01 +08:00
|
|
|
int ret = 0, fput_needed;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
filp = fget_light(fd, &fput_needed);
|
|
|
|
if (unlikely(!filp))
|
|
|
|
return -EBADF;
|
|
|
|
|
|
|
|
/* verify that this is indeed an inotify instance */
|
|
|
|
if (unlikely(filp->f_op != &inotify_fops)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
group = filp->private_data;
|
2006-06-02 04:10:59 +08:00
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
spin_lock(&group->inotify_data.idr_lock);
|
|
|
|
entry = idr_find(&group->inotify_data.idr, wd);
|
|
|
|
if (unlikely(!entry)) {
|
|
|
|
spin_unlock(&group->inotify_data.idr_lock);
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
fsnotify_get_mark(entry);
|
|
|
|
spin_unlock(&group->inotify_data.idr_lock);
|
|
|
|
|
2009-06-13 04:04:26 +08:00
|
|
|
fsnotify_destroy_mark_by_entry(entry);
|
2009-05-22 05:02:01 +08:00
|
|
|
fsnotify_put_mark(entry);
|
2006-06-02 04:10:59 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
fput_light(filp, fput_needed);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
|
|
|
static int
|
2006-06-02 04:10:59 +08:00
|
|
|
inotify_get_sb(struct file_system_type *fs_type, int flags,
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
|
|
|
const char *dev_name, void *data, struct vfsmount *mnt)
|
2006-06-02 04:10:59 +08:00
|
|
|
{
|
2007-10-17 14:30:13 +08:00
|
|
|
return get_sb_pseudo(fs_type, "inotify", NULL,
|
|
|
|
INOTIFYFS_SUPER_MAGIC, mnt);
|
2006-06-02 04:10:59 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct file_system_type inotify_fs_type = {
|
2009-05-22 05:02:01 +08:00
|
|
|
.name = "inotifyfs",
|
|
|
|
.get_sb = inotify_get_sb,
|
|
|
|
.kill_sb = kill_anon_super,
|
2006-06-02 04:10:59 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* inotify_user_setup - Our initialization function. Note that we cannnot return
|
|
|
|
* error because we have compiled-in VFS hooks. So an (unlikely) failure here
|
|
|
|
* must result in panic().
|
|
|
|
*/
|
|
|
|
static int __init inotify_user_setup(void)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = register_filesystem(&inotify_fs_type);
|
|
|
|
if (unlikely(ret))
|
|
|
|
panic("inotify: register_filesystem returned %d!\n", ret);
|
|
|
|
|
|
|
|
inotify_mnt = kern_mount(&inotify_fs_type);
|
|
|
|
if (IS_ERR(inotify_mnt))
|
|
|
|
panic("inotify: kern_mount ret %ld!\n", PTR_ERR(inotify_mnt));
|
|
|
|
|
2009-05-22 05:02:01 +08:00
|
|
|
inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark_entry, SLAB_PANIC);
|
|
|
|
event_priv_cachep = KMEM_CACHE(inotify_event_private_data, SLAB_PANIC);
|
|
|
|
|
2006-06-02 04:10:59 +08:00
|
|
|
inotify_max_queued_events = 16384;
|
|
|
|
inotify_max_user_instances = 128;
|
|
|
|
inotify_max_user_watches = 8192;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
module_init(inotify_user_setup);
|