// SPDX-License-Identifier: GPL-2.0-only/* *  linux/fs/pnode.c * * (C) Copyright IBM Corporation 2005. *	Author : Ram Pai (linuxram@us.ibm.com) */#include <linux/mnt_namespace.h>#include <linux/mount.h>#include <linux/fs.h>#include <linux/nsproxy.h>#include <uapi/linux/mount.h>#include "internal.h"#include "pnode.h" /* return the next shared peer mount of @p */static inline struct mount *next_peer(struct mount *p){	return list_entry(p->mnt_share.next, struct mount, mnt_share);} static inline struct mount *first_slave(struct mount *p){	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);} static inline struct mount *last_slave(struct mount *p){	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);} static inline struct mount *next_slave(struct mount *p){	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);} static struct mount *get_peer_under_root(struct mount *mnt,					 struct mnt_namespace *ns,					 const struct path *root){	struct mount *m = mnt; 	do {		/* Check the namespace first for optimization */		if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root))			return m; 		m = next_peer(m);	} while (m != mnt); 	return NULL;} /* * Get ID of closest dominating peer group having a representative * under the given root. * * Caller must hold namespace_sem */int get_dominating_id(struct mount *mnt, const struct path *root){	struct mount *m; 	for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) {		struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root);		if (d)			return d->mnt_group_id;	} 	return 0;} static int do_make_slave(struct mount *mnt){	struct mount *master, *slave_mnt; 	if (list_empty(&mnt->mnt_share)) {		if (IS_MNT_SHARED(mnt)) {			mnt_release_group_id(mnt);			CLEAR_MNT_SHARED(mnt);		}		master = mnt->mnt_master;		if (!master) {			struct list_head *p = &mnt->mnt_slave_list;			while (!list_empty(p)) {				slave_mnt = list_first_entry(p,						struct mount, mnt_slave);				list_del_init(&slave_mnt->mnt_slave);				slave_mnt->mnt_master = NULL;			}			return 0;		}	} else {		struct mount *m;		/*		 * slave 'mnt' to a peer mount that has the		 * same root dentry. If none is available then		 * slave it to anything that is available.		 */		for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) {			if (m->mnt.mnt_root == mnt->mnt.mnt_root) {				master = m;				break;			}		}		list_del_init(&mnt->mnt_share);		mnt->mnt_group_id = 0;		CLEAR_MNT_SHARED(mnt);	}	list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)		slave_mnt->mnt_master = master;	list_move(&mnt->mnt_slave, &master->mnt_slave_list);	list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);	INIT_LIST_HEAD(&mnt->mnt_slave_list);	mnt->mnt_master = master;	return 0;} /* * vfsmount lock must be held for write */void change_mnt_propagation(struct mount *mnt, int type){	if (type == MS_SHARED) {		set_mnt_shared(mnt);		return;	}	do_make_slave(mnt);	if (type != MS_SLAVE) {		list_del_init(&mnt->mnt_slave);		mnt->mnt_master = NULL;		if (type == MS_UNBINDABLE)			mnt->mnt.mnt_flags |= MNT_UNBINDABLE;		else			mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;	}} /* * get the next mount in the propagation tree. * @m: the mount seen last * @origin: the original mount from where the tree walk initiated * * Note that peer groups form contiguous segments of slave lists. * We rely on that in get_source() to be able to find out if * vfsmount found while iterating with propagation_next() is * a peer of one we'd found earlier. */static struct mount *propagation_next(struct mount *m,					 struct mount *origin){	/* are there any slaves of this mount? */	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))		return first_slave(m); 	while (1) {		struct mount *master = m->mnt_master; 		if (master == origin->mnt_master) {			struct mount *next = next_peer(m);			return (next == origin) ? NULL : next;		} else if (m->mnt_slave.next != &master->mnt_slave_list)			return next_slave(m); 		/* back at master */		m = master;	}} static struct mount *skip_propagation_subtree(struct mount *m,						struct mount *origin){	/*	 * Advance m such that propagation_next will not return	 * the slaves of m.	 */	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))		m = last_slave(m); 	return m;} static struct mount *next_group(struct mount *m, struct mount *origin){	while (1) {		while (1) {			struct mount *next;			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))				return first_slave(m);			next = next_peer(m);			if (m->mnt_group_id == origin->mnt_group_id) {				if (next == origin)					return NULL;			} else if (m->mnt_slave.next != &next->mnt_slave)				break;			m = next;		}		/* m is the last peer */		while (1) {			struct mount *master = m->mnt_master;			if (m->mnt_slave.next != &master->mnt_slave_list)				return next_slave(m);			m = next_peer(master);			if (master->mnt_group_id == origin->mnt_group_id)				break;			if (master->mnt_slave.next == &m->mnt_slave)				break;			m = master;		}		if (m == origin)			return NULL;	}} /* all accesses are serialized by namespace_sem */static struct mount *last_dest, *first_source, *last_source, *dest_master;static struct hlist_head *list; static inline bool peers(const struct mount *m1, const struct mount *m2){	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;} static int propagate_one(struct mount *m, struct mountpoint *dest_mp){	struct mount *child;	int type;	/* skip ones added by this propagate_mnt() */	if (IS_MNT_NEW(m))		return 0;	/* skip if mountpoint isn't visible in m */	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))		return 0;	/* skip if m is in the anon_ns */	if (is_anon_ns(m->mnt_ns))		return 0; 	if (peers(m, last_dest)) {		type = CL_MAKE_SHARED;	} else {		struct mount *n, *p;		bool done;		for (n = m; ; n = p) {			p = n->mnt_master;			if (p == dest_master || IS_MNT_MARKED(p))				break;		}		do {			struct mount *parent = last_source->mnt_parent;			if (peers(last_source, first_source))				break;			done = parent->mnt_master == p;			if (done && peers(n, parent))				break;			last_source = last_source->mnt_master;		} while (!done); 		type = CL_SLAVE;		/* beginning of peer group among the slaves? */		if (IS_MNT_SHARED(m))			type |= CL_MAKE_SHARED;	}			child = copy_tree(last_source, last_source->mnt.mnt_root, type);	if (IS_ERR(child))		return PTR_ERR(child);	read_seqlock_excl(&mount_lock);	mnt_set_mountpoint(m, dest_mp, child);	if (m->mnt_master != dest_master)		SET_MNT_MARK(m->mnt_master);	read_sequnlock_excl(&mount_lock);	last_dest = m;	last_source = child;	hlist_add_head(&child->mnt_hash, list);	return count_mounts(m->mnt_ns, child);} /* * mount 'source_mnt' under the destination 'dest_mnt' at * dentry 'dest_dentry'. And propagate that mount to * all the peer and slave mounts of 'dest_mnt'. * Link all the new mounts into a propagation tree headed at * source_mnt. Also link all the new mounts using ->mnt_list * headed at source_mnt's ->mnt_list * * @dest_mnt: destination mount. * @dest_dentry: destination dentry. * @source_mnt: source mount. * @tree_list : list of heads of trees to be attached. */int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,		    struct mount *source_mnt, struct hlist_head *tree_list){	struct mount *m, *n;	int ret = 0; 	/*	 * we don't want to bother passing tons of arguments to	 * propagate_one(); everything is serialized by namespace_sem,	 * so globals will do just fine.	 */	last_dest = dest_mnt;	first_source = source_mnt;	last_source = source_mnt;	list = tree_list;	dest_master = dest_mnt->mnt_master; 	/* all peers of dest_mnt, except dest_mnt itself */	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {		ret = propagate_one(n, dest_mp);		if (ret)			goto out;	} 	/* all slave groups */	for (m = next_group(dest_mnt, dest_mnt); m;			m = next_group(m, dest_mnt)) {		/* everything in that slave group */		n = m;		do {			ret = propagate_one(n, dest_mp);			if (ret)				goto out;			n = next_peer(n);		} while (n != m);	}out:	read_seqlock_excl(&mount_lock);	hlist_for_each_entry(n, tree_list, mnt_hash) {		m = n->mnt_parent;		if (m->mnt_master != dest_mnt->mnt_master)			CLEAR_MNT_MARK(m->mnt_master);	}	read_sequnlock_excl(&mount_lock);	return ret;} static struct mount *find_topper(struct mount *mnt){	/* If there is exactly one mount covering mnt completely return it. */	struct mount *child; 	if (!list_is_singular(&mnt->mnt_mounts))		return NULL; 	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);	if (child->mnt_mountpoint != mnt->mnt.mnt_root)		return NULL; 	return child;} /* * return true if the refcount is greater than count */static inline int do_refcount_check(struct mount *mnt, int count){	return mnt_get_count(mnt) > count;} /** * propagation_would_overmount - check whether propagation from @from *                               would overmount @to * @from: shared mount * @to:   mount to check * @mp:   future mountpoint of @to on @from * * If @from propagates mounts to @to, @from and @to must either be peers * or one of the masters in the hierarchy of masters of @to must be a * peer of @from. * * If the root of the @to mount is equal to the future mountpoint @mp of * the @to mount on @from then @to will be overmounted by whatever is * propagated to it. * * Context: This function expects namespace_lock() to be held and that *          @mp is stable. * Return: If @from overmounts @to, true is returned, false if not. */bool propagation_would_overmount(const struct mount *from,				 const struct mount *to,				 const struct mountpoint *mp){	if (!IS_MNT_SHARED(from))		return false; 	if (to->mnt.mnt_root != mp->m_dentry)		return false; 	for (const struct mount *m = to; m; m = m->mnt_master) {		if (peers(from, m))			return true;	} 	return false;} /* * check if the mount 'mnt' can be unmounted successfully. * @mnt: the mount to be checked for unmount * NOTE: unmounting 'mnt' would naturally propagate to all * other mounts its parent propagates to. * Check if any of these mounts that **do not have submounts** * have more references than 'refcnt'. If so return busy. * * vfsmount lock must be held for write */int propagate_mount_busy(struct mount *mnt, int refcnt){	struct mount *m, *child, *topper;	struct mount *parent = mnt->mnt_parent; 	if (mnt == parent)		return do_refcount_check(mnt, refcnt); 	/*	 * quickly check if the current mount can be unmounted.	 * If not, we don't have to go checking for all other	 * mounts	 */	if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt))		return 1; 	for (m = propagation_next(parent, parent); m;	     		m = propagation_next(m, parent)) {		int count = 1;		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);		if (!child)			continue; 		/* Is there exactly one mount on the child that covers		 * it completely whose reference should be ignored?		 */		topper = find_topper(child);		if (topper)			count += 1;		else if (!list_empty(&child->mnt_mounts))			continue; 		if (do_refcount_check(child, count))			return 1;	}	return 0;} /* * Clear MNT_LOCKED when it can be shown to be safe. * * mount_lock lock must be held for write */void propagate_mount_unlock(struct mount *mnt){	struct mount *parent = mnt->mnt_parent;	struct mount *m, *child; 	BUG_ON(parent == mnt); 	for (m = propagation_next(parent, parent); m;			m = propagation_next(m, parent)) {		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);		if (child)			child->mnt.mnt_flags &= ~MNT_LOCKED;	}} static void umount_one(struct mount *mnt, struct list_head *to_umount){	CLEAR_MNT_MARK(mnt);	mnt->mnt.mnt_flags |= MNT_UMOUNT;	list_del_init(&mnt->mnt_child);	list_del_init(&mnt->mnt_umounting);	move_from_ns(mnt, to_umount);} /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */static bool __propagate_umount(struct mount *mnt,			       struct list_head *to_umount,			       struct list_head *to_restore){	bool progress = false;	struct mount *child; 	/*	 * The state of the parent won't change if this mount is	 * already unmounted or marked as without children.	 */	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))		goto out; 	/* Verify topper is the only grandchild that has not been	 * speculatively unmounted.	 */	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {		if (child->mnt_mountpoint == mnt->mnt.mnt_root)			continue;		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))			continue;

Lines 1–500 of 643. Load more