path: root/fs/notify/mark.c

/*
 *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
 *
 *  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.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; see the file COPYING.  If not, write to
 *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 * fsnotify inode mark locking/lifetime/and refcnting
 *
 * REFCNT:
 * The group->recnt and mark->refcnt tell how many "things" in the kernel
 * currently are referencing the objects. Both kind of objects typically will
 * live inside the kernel with a refcnt of 2, one for its creation and one for
 * the reference a group and a mark hold to each other.
 * If you are holding the appropriate locks, you can take a reference and the
 * object itself is guaranteed to survive until the reference is dropped.
 *
 * LOCKING:
 * There are 3 locks involved with fsnotify inode marks and they MUST be taken
 * in order as follows:
 *
 * group->mark_mutex
 * mark->lock
 * mark->connector->lock
 *
 * group->mark_mutex protects the marks_list anchored inside a given group and
 * each mark is hooked via the g_list.  It also protects the groups private
 * data (i.e group limits).

 * mark->lock protects the marks attributes like its masks and flags.
 * Furthermore it protects the access to a reference of the group that the mark
 * is assigned to as well as the access to a reference of the inode/vfsmount
 * that is being watched by the mark.
 *
 * mark->connector->lock protects the list of marks anchored inside an
 * inode / vfsmount and each mark is hooked via the i_list.
 *
 * A list of notification marks relating to inode / mnt is contained in
 * fsnotify_mark_connector. That structure is alive as long as there are any
 * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets
 * detached from fsnotify_mark_connector when last reference to the mark is
 * dropped.  Thus having mark reference is enough to protect mark->connector
 * pointer and to make sure fsnotify_mark_connector cannot disappear. Also
 * because we remove mark from g_list before dropping mark reference associated
 * with that, any mark found through g_list is guaranteed to have
 * mark->connector set until we drop group->mark_mutex.
 *
 * LIFETIME:
 * Inode marks survive between when they are added to an inode and when their
 * refcnt==0. Marks are also protected by fsnotify_mark_srcu.
 *
 * The inode mark can be cleared for a number of different reasons including:
 * - The inode is unlinked for the last time.  (fsnotify_inode_remove)
 * - The inode is being evicted from cache. (fsnotify_inode_delete)
 * - The fs the inode is on is unmounted.  (fsnotify_inode_delete/fsnotify_unmount_inodes)
 * - Something explicitly requests that it be removed.  (fsnotify_destroy_mark)
 * - The fsnotify_group associated with the mark is going away and all such marks
 *   need to be cleaned up. (fsnotify_clear_marks_by_group)
 *
 * This has the very interesting property of being able to run concurrently with
 * any (or all) other directions.
 */

#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/srcu.h>

#include <linux/atomic.h>

#include <linux/fsnotify_backend.h>
#include "fsnotify.h"

#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */

struct srcu_struct fsnotify_mark_srcu;
struct kmem_cache *fsnotify_mark_connector_cachep;

static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
static struct fsnotify_mark_connector *connector_destroy_list;

static void fsnotify_mark_destroy_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);

static void fsnotify_connector_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);

void fsnotify_get_mark(struct fsnotify_mark *mark)
{
	WARN_ON_ONCE(!atomic_read(&mark->refcnt));
	atomic_inc(&mark->refcnt);
}

static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
	u32 new_mask = 0;
	struct fsnotify_mark *mark;

	assert_spin_locked(&conn->lock);
	hlist_for_each_entry(mark, &conn->list, obj_list) {
		if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
			new_mask |= mark->mask;
	}
	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
		conn->inode->i_fsnotify_mask = new_mask;
	else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT)
		real_mount(conn->mnt)->mnt_fsnotify_mask = new_mask;
}

/*
 * Calculate mask of events for a list of marks. The caller must make sure
 * connector and connector->inode cannot disappear under us.  Callers achieve
 * this by holding a mark->lock or mark->group->mark_mutex for a mark on this
 * list.
 */
void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
	if (!conn)
		return;

	spin_lock(&conn->lock);
	__fsnotify_recalc_mask(conn);
	spin_unlock(&conn->lock);
	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
		__fsnotify_update_child_dentry_flags(conn->inode);
}

/* Free all connectors queued for freeing once SRCU period ends */
static void fsnotify_connector_destroy_workfn(struct work_struct *work)
{
	struct fsnotify_mark_connector *conn, *free;

	spin_lock(&destroy_lock);
	conn = connector_destroy_list;
	connector_destroy_list = NULL;
	spin_unlock(&destroy_lock);

	synchronize_srcu(&fsnotify_mark_srcu);
	while (conn) {
		free = conn;
		conn = conn->destroy_next;
		kmem_cache_free(fsnotify_mark_connector_cachep, free);
	}
}

static struct inode *fsnotify_detach_connector_from_object(
					struct fsnotify_mark_connector *conn)
{
	struct inode *inode = NULL;

	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
		inode = conn->inode;
		rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
		inode->i_fsnotify_mask = 0;
		conn->inode = NULL;
		conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
	} else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
		rcu_assign_pointer(real_mount(conn->mnt)->mnt_fsnotify_marks,
				   NULL);
		real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
		conn->mnt = NULL;
		conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
	}

	return inode;
}

static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
{
	struct fsnotify_group *group = mark->group;

	if (WARN_ON_ONCE(!group))
		return;
	group->ops->free_mark(mark);
	fsnotify_put_group(group);
}

void fsnotify_put_mark(struct fsnotify_mark *mark)
{
	struct fsnotify_mark_connector *conn;
	struct inode *inode = NULL;
	bool free_conn = false;

	/* Catch marks that were actually never attached to object */
	if (!mark->connector) {
		if (atomic_dec_and_test(&mark->refcnt))
			fsnotify_final_mark_destroy(mark);
		return;
	}

	/*
	 * We have to be careful so that traversals of obj_list under lock can
	 * safely grab mark reference.
	 */
	if (!atomic_dec_and_lock(&mark->refcnt, &mark->connector->lock))
		return;

	conn = mark->connector;
	hlist_del_init_rcu(&mark->obj_list);
	if (hlist_empty(&conn->list)) {
		inode = fsnotify_detach_connector_from_object(conn);
		free_conn = true;
	} else {
		__fsnotify_recalc_mask(conn);
	}
	mark->connector = NULL;
	spin_unlock(&conn->lock);

	iput(inode);

	if (free_conn) {
		spin_lock(&destroy_lock);
		conn->destroy_next = connector_destroy_list;
		connector_destroy_list = conn;
		spin_unlock(&destroy_lock);
		queue_work(system_unbound_wq, &connector_reaper_work);
	}
	/*
	 * Note that we didn't update flags telling whether inode cares about
	 * what's happening with children. We update these flags from
	 * __fsnotify_parent() lazily when next event happens on one of our