fs/notify/fsnotify.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
 */

#include <linux/dcache.h>
#include <linux/fs.h>
#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/srcu.h>

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

/*
 * Clear all of the marks on an inode when it is being evicted from core
 */
void __fsnotify_inode_delete(struct inode *inode)
{
	fsnotify_clear_marks_by_inode(inode);
}
EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);

void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
{
	fsnotify_clear_marks_by_mount(mnt);
}

/**
 * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
 * @sb: superblock being unmounted.
 *
 * Called during unmount with no locks held, so needs to be safe against
 * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
 */
static void fsnotify_unmount_inodes(struct super_block *sb)
{
	struct inode *inode, *iput_inode = NULL;

	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		/*
		 * We cannot __iget() an inode in state I_FREEING,
		 * I_WILL_FREE, or I_NEW which is fine because by that point
		 * the inode cannot have any associated watches.
		 */
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		/*
		 * If i_count is zero, the inode cannot have any watches and
		 * doing an __iget/iput with SB_ACTIVE clear would actually
		 * evict all inodes with zero i_count from icache which is
		 * unnecessarily violent and may in fact be illegal to do.
		 * However, we should have been called /after/ evict_inodes
		 * removed all zero refcount inodes, in any case.  Test to
		 * be sure.
		 */
		if (!atomic_read(&inode->i_count)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&sb->s_inode_list_lock);

		if (iput_inode)
			iput(iput_inode);

		/* for each watch, send FS_UNMOUNT and then remove it */
		fsnotify_inode(inode, FS_UNMOUNT);

		fsnotify_inode_delete(inode);

		iput_inode = inode;

		cond_resched();
		spin_lock(&sb->s_inode_list_lock);
	}
	spin_unlock(&sb->s_inode_list_lock);

	if (iput_inode)
		iput(iput_inode);
	/* Wait for outstanding inode references from connectors */
	wait_var_event(&sb->s_fsnotify_inode_refs,
		       !atomic_long_read(&sb->s_fsnotify_inode_refs));
}

void fsnotify_sb_delete(struct super_block *sb)
{
	fsnotify_unmount_inodes(sb);
	fsnotify_clear_marks_by_sb(sb);
}

/*
 * Given an inode, first check if we care what happens to our children.  Inotify
 * and dnotify both tell their parents about events.  If we care about any event
 * on a child we run all of our children and set a dentry flag saying that the
 * parent cares.  Thus when an event happens on a child it can quickly tell if
 * if there is a need to find a parent and send the event to the parent.
 */
void __fsnotify_update_child_dentry_flags(struct inode *inode)
{
	struct dentry *alias;
	int watched;

	if (!S_ISDIR(inode->i_mode))
		return;

	/* determine if the children should tell inode about their events */
	watched = fsnotify_inode_watches_children(inode);

	spin_lock(&inode->i_lock);
	/* run all of the dentries associated with this inode.  Since this is a
	 * directory, there damn well better only be one item on this list */
	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
		struct dentry *child;

		/* run all of the children of the original inode and fix their
		 * d_flags to indicate parental interest (their parent is the
		 * original inode) */
		spin_lock(&alias->d_lock);
		list_for_each_entry(child, &alias->d_subdirs, d_child) {
			if (!child->d_inode)
				continue;

			spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
			if (watched)
				child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
			else
				child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
			spin_unlock(&child->d_lock);
		}
		spin_unlock(&alias->d_lock);
	}
	spin_unlock(&inode->i_lock);
}

/* Are inode/sb/mount interested in parent and name info with this event? */
static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt,
					__u32 mask)
{
	__u32 marks_mask = 0;

	/* We only send parent/name to inode/sb/mount for events on non-dir */
	if (mask & FS_ISDIR)
		return false;

	/* Did either inode/sb/mount subscribe for events with parent/name? */
	marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
	marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
	if (mnt)
		marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask);

	/* Did they subscribe for this event with parent/name info? */
	return mask & marks_mask;
}

/*
 * Notify this dentry's parent about a child's events with child name info
 * if parent is watching or if inode/sb/mount are interested in events with
 * parent and name info.
 *
 * Notify only the child without name info if parent is not watching and
 * inode/sb/mount are not interested in events with parent and name info.
 */
int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
		      int data_type)
{
	const struct path *path = fsnotify_data_path(data, data_type);
	struct mount *mnt = path ? real_mount(path->mnt) : NULL;
	struct inode *inode = d_inode(dentry);
	struct dentry *parent;
	bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
	__u32 p_mask;
	struct inode *p_inode = NULL;
	struct name_snapshot name;
	struct qstr *file_name = NULL;
	int ret = 0;

	/*
	 * Do inode/sb/mount care about parent and name info on non-dir?
	 * Do they care about any event at all?
	 */
	if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks &&
	    (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched)
		return 0;

	parent = NULL;
	if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask))
		goto notify;

	/* Does parent inode care about events on children? */
	parent = dget_parent(dentry);
	p_inode = parent->d_inode;
	p_mask = fsnotify_inode_watches_children(p_inode);
	if (unlikely(parent_watched && !p_mask))
		__fsnotify_update_child_dentry_flags(p_inode);

	/*
	 * Include parent/name in notification either if some notification
	 * groups require parent info (!parent_watched case) or the parent is
	 * interested in this event.
	 */
	if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) {
		/* When notifying parent, child should be passed as data */
		WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));

		/* Notify both parent and child with child name info */
		take_dentry_name_snapshot(&name, dentry);
		file_name = &name.name;
		if (parent_watched)
			mask |= FS_EVENT_ON_CHILD;
	}

notify:
	ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0);

	if (file_name)
		release_dentry_name_snapshot(&name);
	dput(parent);

	return ret;
}
EXPORT_SYMBOL_GPL(__fsnotify_parent);

static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
				 const void *data, int data_type,
				 struct inode *dir, const struct qstr *name,
				 u32 cookie, struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
	struct inode *inode = fsnotify_data_inode(data, data_type);
	const struct fsnotify_ops *ops = group->ops;
	int ret;

	if (WARN_ON_ONCE(!ops->handle_inode_event))
		return 0;

	if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
	    WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
		return 0;

	/*
	 * An event can be sent on child mark iterator instead of inode mark
	 * iterator because of other groups that have interest of this inode
	 * and have marks on both parent and child.  We can simplify this case.
	 */
	if (!inode_mark) {
		inode_mark = child_mark;
		child_mark = NULL;
		dir = NULL;
		name = NULL;
	}

	ret = ops->handle_inode_event(inode_mark, mask, inode, dir, name);
	if (ret || !child_mark)
		return ret;

	/*
	 * Some events can be sent on both parent dir and child marks
	 * (e.g. FS_ATTRIB).  If both parent dir and child are watching,
	 * report the event once to parent dir with name and once to child
	 * without name.
	 */
	return ops->handle_inode_event(child_mark, mask, inode, NULL, NULL);
}

static int send_to_group(__u32 mask, const void *data, int data_type,
			 struct inode *dir, const struct qstr *file_name,
			 u32 cookie, struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_group *group = NULL;
	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
	__u32 marks_mask = 0;
	__u32 marks_ignored_mask = 0;
	struct fsnotify_mark *mark;
	int type;

	if (WARN_ON(!iter_info->report_mask))
		return 0;

	/* clear ignored on inode modification */
	if (mask & FS_MODIFY) {
		fsnotify_foreach_obj_type(type) {
			if (!fsnotify_iter_should_report_type(iter_info, type))
				continue;
			mark = iter_info->marks[type];
			if (mark &&
			    !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
				mark->ignored_mask = 0;
		}
	}

	fsnotify_foreach_obj_type(type) {
		if (!fsnotify_iter_should_report_type(iter_info, type))
			continue;
		mark = iter_info->marks[type];
		/* does the object mark tell us to do something? */
		if (mark) {
			group = mark->group;
			marks_mask |= mark->mask;
			marks_ignored_mask |= mark->ignored_mask;
		}
	}

	pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
		 __func__, group, mask, marks_mask, marks_ignored_mask,
		 data, data_type, dir, cookie);

	if (!(test_mask & marks_mask & ~marks_ignored_mask))
		return 0;

	if (group->ops->handle_event) {
		return group->ops->handle_event(group, mask, data, data_type, dir,
						file_name, cookie, iter_info);
	}

	return fsnotify_handle_event(group, mask, data, data_type, dir,
				     file_name, cookie, iter_info);
}

static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
{
	struct fsnotify_mark_connector *conn;
	struct hlist_node *node = NULL;

	conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
	if (conn)
		node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu);

	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}

static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
{
	struct hlist_node *node = NULL;

	if (mark)
		node = srcu_dereference(mark->obj_list.next,
					&fsnotify_mark_srcu);

	return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}

/*
 * iter_info is a multi head priority queue of marks.
 * Pick a subset of marks from queue heads, all with the
 * same group and set the report_mask for selected subset.
 * Returns the report_mask of the selected subset.
 */
static unsigned int fsnotify_iter_select_report_types(
		struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_group *max_prio_group = NULL;
	struct fsnotify_mark *mark;
	int type;

	/* Choose max prio group among groups of all queue heads */
	fsnotify_foreach_obj_type(type) {
		mark = iter_info->marks[type];
		if (mark &&
		    fsnotify_compare_groups(max_prio_group, mark->group) > 0)
			max_prio_group = mark->group;
	}

	if (!max_prio_group)
		return 0;

	/* Set the report mask for marks from same group as max prio group */
	iter_info->report_mask = 0;
	fsnotify_foreach_obj_type(type) {
		mark = iter_info->marks[type];
		if (mark &&
		    fsnotify_compare_groups(max_prio_group, mark->group) == 0)
			fsnotify_iter_set_report_type(iter_info, type);
	}

	return iter_info->report_mask;
}

/*
 * Pop from iter_info multi head queue, the marks that were iterated in the
 * current iteration step.
 */
static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
{
	int type;

	fsnotify_foreach_obj_type(type) {
		if (fsnotify_iter_should_report_type(iter_info, type))
			iter_info->marks[type] =
				fsnotify_next_mark(iter_info->marks[type]);
	}
}

/*
 * fsnotify - This is the main call to fsnotify.
 *
 * The VFS calls into hook specific functions in linux/fsnotify.h.
 * Those functions then in turn call here.  Here will call out to all of the
 * registered fsnotify_group.  Those groups can then use the notification event
 * in whatever means they feel necessary.
 *
 * @mask:	event type and flags
 * @data:	object that event happened on
 * @data_type:	type of object for fanotify_data_XXX() accessors
 * @dir:	optional directory associated with event -
 *		if @file_name is not NULL, this is the directory that
 *		@file_name is relative to
 * @file_name:	optional file name associated with event
 * @inode:	optional inode associated with event -
 *		either @dir or @inode must be non-NULL.
 *		if both are non-NULL event may be reported to both.
 * @cookie:	inotify rename cookie
 */
int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
	     const struct qstr *file_name, struct inode *inode, u32 cookie)
{
	const struct path *path = fsnotify_data_path(data, data_type);
	struct fsnotify_iter_info iter_info = {};
	struct super_block *sb;
	struct mount *mnt = NULL;
	struct inode *child = NULL;
	int ret = 0;
	__u32 test_mask, marks_mask;

	if (path)
		mnt = real_mount(path->mnt);

	if (!inode) {
		/* Dirent event - report on TYPE_INODE to dir */
		inode = dir;
	} else if (mask & FS_EVENT_ON_CHILD) {
		/*
		 * Event on child - report on TYPE_INODE to dir if it is
		 * watching children and on TYPE_CHILD to child.
		 */
		child = inode;
		inode = dir;
	}
	sb = inode->i_sb;

	/*
	 * Optimization: srcu_read_lock() has a memory barrier which can
	 * be expensive.  It protects walking the *_fsnotify_marks lists.
	 * However, if we do not walk the lists, we do not have to do
	 * SRCU because we have no references to any objects and do not
	 * need SRCU to keep them "alive".
	 */
	if (!sb->s_fsnotify_marks &&
	    (!mnt || !mnt->mnt_fsnotify_marks) &&
	    (!inode || !inode->i_fsnotify_marks) &&
	    (!child || !child->i_fsnotify_marks))
		return 0;

	marks_mask = sb->s_fsnotify_mask;
	if (mnt)
		marks_mask |= mnt->mnt_fsnotify_mask;
	if (inode)
		marks_mask |= inode->i_fsnotify_mask;
	if (child)
		marks_mask |= child->i_fsnotify_mask;


	/*
	 * if this is a modify event we may need to clear the ignored masks
	 * otherwise return if none of the marks care about this type of event.
	 */
	test_mask = (mask & ALL_FSNOTIFY_EVENTS);
	if (!(mask & FS_MODIFY) && !(test_mask & marks_mask))
		return 0;

	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);

	iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] =
		fsnotify_first_mark(&sb->s_fsnotify_marks);
	if (mnt) {
		iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] =
			fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
	}
	if (inode) {
		iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
			fsnotify_first_mark(&inode->i_fsnotify_marks);
	}
	if (child) {
		iter_info.marks[FSNOTIFY_OBJ_TYPE_CHILD] =
			fsnotify_first_mark(&child->i_fsnotify_marks);
	}

	/*
	 * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
	 * ignore masks are properly reflected for mount/sb mark notifications.
	 * That's why this traversal is so complicated...
	 */
	while (fsnotify_iter_select_report_types(&iter_info)) {
		ret = send_to_group(mask, data, data_type, dir, file_name,
				    cookie, &iter_info);

		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
			goto out;

		fsnotify_iter_next(&iter_info);
	}
	ret = 0;
out:
	srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);

	return ret;
}
EXPORT_SYMBOL_GPL(fsnotify);

static __init int fsnotify_init(void)
{
	int ret;

	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);

	ret = init_srcu_struct(&fsnotify_mark_srcu);
	if (ret)
		panic("initializing fsnotify_mark_srcu");

	fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
						    SLAB_PANIC);

	return 0;
}
core_initcall(fsnotify_init);