linux-stable/fs/notify/group.c
Amir Goldstein 5b8fea65d1 fanotify: configurable limits via sysfs
fanotify has some hardcoded limits. The only APIs to escape those limits
are FAN_UNLIMITED_QUEUE and FAN_UNLIMITED_MARKS.

Allow finer grained tuning of the system limits via sysfs tunables under
/proc/sys/fs/fanotify, similar to tunables under /proc/sys/fs/inotify,
with some minor differences.

- max_queued_events - global system tunable for group queue size limit.
  Like the inotify tunable with the same name, it defaults to 16384 and
  applies on initialization of a new group.

- max_user_marks - user ns tunable for marks limit per user.
  Like the inotify tunable named max_user_watches, on a machine with
  sufficient RAM and it defaults to 1048576 in init userns and can be
  further limited per containing user ns.

- max_user_groups - user ns tunable for number of groups per user.
  Like the inotify tunable named max_user_instances, it defaults to 128
  in init userns and can be further limited per containing user ns.

The slightly different tunable names used for fanotify are derived from
the "group" and "mark" terminology used in the fanotify man pages and
throughout the code.

Considering the fact that the default value for max_user_instances was
increased in kernel v5.10 from 8192 to 1048576, leaving the legacy
fanotify limit of 8192 marks per group in addition to the max_user_marks
limit makes little sense, so the per group marks limit has been removed.

Note that when a group is initialized with FAN_UNLIMITED_MARKS, its own
marks are not accounted in the per user marks account, so in effect the
limit of max_user_marks is only for the collection of groups that are
not initialized with FAN_UNLIMITED_MARKS.

Link: https://lore.kernel.org/r/20210304112921.3996419-2-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
2021-03-16 16:49:31 +01:00

163 lines
4.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
*/
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/srcu.h>
#include <linux/rculist.h>
#include <linux/wait.h>
#include <linux/memcontrol.h>
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
#include <linux/atomic.h>
/*
* Final freeing of a group
*/
static void fsnotify_final_destroy_group(struct fsnotify_group *group)
{
if (group->ops->free_group_priv)
group->ops->free_group_priv(group);
mem_cgroup_put(group->memcg);
mutex_destroy(&group->mark_mutex);
kfree(group);
}
/*
* Stop queueing new events for this group. Once this function returns
* fsnotify_add_event() will not add any new events to the group's queue.
*/
void fsnotify_group_stop_queueing(struct fsnotify_group *group)
{
spin_lock(&group->notification_lock);
group->shutdown = true;
spin_unlock(&group->notification_lock);
}
/*
* Trying to get rid of a group. Remove all marks, flush all events and release
* the group reference.
* Note that another thread calling fsnotify_clear_marks_by_group() may still
* hold a ref to the group.
*/
void fsnotify_destroy_group(struct fsnotify_group *group)
{
/*
* Stop queueing new events. The code below is careful enough to not
* require this but fanotify needs to stop queuing events even before
* fsnotify_destroy_group() is called and this makes the other callers
* of fsnotify_destroy_group() to see the same behavior.
*/
fsnotify_group_stop_queueing(group);
/* Clear all marks for this group and queue them for destruction */
fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES_MASK);
/*
* Some marks can still be pinned when waiting for response from
* userspace. Wait for those now. fsnotify_prepare_user_wait() will
* not succeed now so this wait is race-free.
*/
wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
/*
* Wait until all marks get really destroyed. We could actually destroy
* them ourselves instead of waiting for worker to do it, however that
* would be racy as worker can already be processing some marks before
* we even entered fsnotify_destroy_group().
*/
fsnotify_wait_marks_destroyed();
/*
* Since we have waited for fsnotify_mark_srcu in
* fsnotify_mark_destroy_list() there can be no outstanding event
* notification against this group. So clearing the notification queue
* of all events is reliable now.
*/
fsnotify_flush_notify(group);
/*
* Destroy overflow event (we cannot use fsnotify_destroy_event() as
* that deliberately ignores overflow events.
*/
if (group->overflow_event)
group->ops->free_event(group->overflow_event);
fsnotify_put_group(group);
}
/*
* Get reference to a group.
*/
void fsnotify_get_group(struct fsnotify_group *group)
{
refcount_inc(&group->refcnt);
}
/*
* Drop a reference to a group. Free it if it's through.
*/
void fsnotify_put_group(struct fsnotify_group *group)
{
if (refcount_dec_and_test(&group->refcnt))
fsnotify_final_destroy_group(group);
}
EXPORT_SYMBOL_GPL(fsnotify_put_group);
static struct fsnotify_group *__fsnotify_alloc_group(
const struct fsnotify_ops *ops, gfp_t gfp)
{
struct fsnotify_group *group;
group = kzalloc(sizeof(struct fsnotify_group), gfp);
if (!group)
return ERR_PTR(-ENOMEM);
/* set to 0 when there a no external references to this group */
refcount_set(&group->refcnt, 1);
atomic_set(&group->user_waits, 0);
spin_lock_init(&group->notification_lock);
INIT_LIST_HEAD(&group->notification_list);
init_waitqueue_head(&group->notification_waitq);
group->max_events = UINT_MAX;
mutex_init(&group->mark_mutex);
INIT_LIST_HEAD(&group->marks_list);
group->ops = ops;
return group;
}
/*
* Create a new fsnotify_group and hold a reference for the group returned.
*/
struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
{
return __fsnotify_alloc_group(ops, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
/*
* Create a new fsnotify_group and hold a reference for the group returned.
*/
struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops)
{
return __fsnotify_alloc_group(ops, GFP_KERNEL_ACCOUNT);
}
EXPORT_SYMBOL_GPL(fsnotify_alloc_user_group);
int fsnotify_fasync(int fd, struct file *file, int on)
{
struct fsnotify_group *group = file->private_data;
return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO;
}