path: root/kernel/nstree.c

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */

#include <linux/nstree.h>
#include <linux/proc_ns.h>
#include <linux/rculist.h>
#include <linux/vfsdebug.h>
#include <linux/user_namespace.h>

static __cacheline_aligned_in_smp DEFINE_SEQLOCK(ns_tree_lock);
static struct rb_root ns_unified_tree = RB_ROOT; /* protected by ns_tree_lock */
static LIST_HEAD(ns_unified_list); /* protected by ns_tree_lock */

/**
 * struct ns_tree - Namespace tree
 * @ns_tree: Rbtree of namespaces of a particular type
 * @ns_list: Sequentially walkable list of all namespaces of this type
 * @type: type of namespaces in this tree
 */
struct ns_tree {
	struct rb_root ns_tree;
	struct list_head ns_list;
	int type;
};

struct ns_tree mnt_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(mnt_ns_tree.ns_list),
	.type = CLONE_NEWNS,
};

struct ns_tree net_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(net_ns_tree.ns_list),
	.type = CLONE_NEWNET,
};
EXPORT_SYMBOL_GPL(net_ns_tree);

struct ns_tree uts_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(uts_ns_tree.ns_list),
	.type = CLONE_NEWUTS,
};

struct ns_tree user_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(user_ns_tree.ns_list),
	.type = CLONE_NEWUSER,
};

struct ns_tree ipc_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(ipc_ns_tree.ns_list),
	.type = CLONE_NEWIPC,
};

struct ns_tree pid_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(pid_ns_tree.ns_list),
	.type = CLONE_NEWPID,
};

struct ns_tree cgroup_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(cgroup_ns_tree.ns_list),
	.type = CLONE_NEWCGROUP,
};

struct ns_tree time_ns_tree = {
	.ns_tree = RB_ROOT,
	.ns_list = LIST_HEAD_INIT(time_ns_tree.ns_list),
	.type = CLONE_NEWTIME,
};

static inline struct ns_common *node_to_ns(const struct rb_node *node)
{
	if (!node)
		return NULL;
	return rb_entry(node, struct ns_common, ns_tree_node);
}

static inline struct ns_common *node_to_ns_unified(const struct rb_node *node)
{
	if (!node)
		return NULL;
	return rb_entry(node, struct ns_common, ns_unified_tree_node);
}

static inline struct ns_common *node_to_ns_owner(const struct rb_node *node)
{
	if (!node)
		return NULL;
	return rb_entry(node, struct ns_common, ns_owner_tree_node);
}

static int ns_id_cmp(u64 id_a, u64 id_b)
{
	if (id_a < id_b)
		return -1;
	if (id_a > id_b)
		return 1;
	return 0;
}

static int ns_cmp(struct rb_node *a, const struct rb_node *b)
{
	return ns_id_cmp(node_to_ns(a)->ns_id, node_to_ns(b)->ns_id);
}

static int ns_cmp_unified(struct rb_node *a, const struct rb_node *b)
{
	return ns_id_cmp(node_to_ns_unified(a)->ns_id, node_to_ns_unified(b)->ns_id);
}

static int ns_cmp_owner(struct rb_node *a, const struct rb_node *b)
{
	return ns_id_cmp(node_to_ns_owner(a)->ns_id, node_to_ns_owner(b)->ns_id);
}

void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree)
{
	struct rb_node *node, *prev;
	const struct proc_ns_operations *ops = ns->ops;

	VFS_WARN_ON_ONCE(!ns->ns_id);
	VFS_WARN_ON_ONCE(ns->ns_type != ns_tree->type);

	write_seqlock(&ns_tree_lock);

	node = rb_find_add_rcu(&ns->ns_tree_node, &ns_tree->ns_tree, ns_cmp);
	/*
	 * If there's no previous entry simply add it after the
	 * head and if there is add it after the previous entry.
	 */
	prev = rb_prev(&ns->ns_tree_node);
	if (!prev)
		list_add_rcu(&ns->ns_list_node, &ns_tree->ns_list);
	else
		list_add_rcu(&ns->ns_list_node, &node_to_ns(prev)->ns_list_node);

	/* Add to unified tree and list */
	rb_find_add_rcu(&ns->ns_unified_tree_node, &ns_unified_tree, ns_cmp_unified);
	prev = rb_prev(&ns->ns_unified_tree_node);
	if (!prev)
		list_add_rcu(&ns->ns_unified_list_node, &ns_unified_list);
	else
		list_add_rcu(&ns->ns_unified_list_node, &node_to_ns_unified(prev)->ns_unified_list_node);

	if (ops) {
		struct user_namespace *user_ns;

		VFS_WARN_ON_ONCE(!ops->owner);
		user_ns = ops->owner(ns);
		if (user_ns) {
			struct ns_common *owner = &user_ns->ns;
			VFS_WARN_ON_ONCE(owner->ns_type != CLONE_NEWUSER);

			/* Insert into owner's rbtree */
			rb_find_add_rcu(&ns->ns_owner_tree_node, &owner->ns_owner_tree, ns_cmp_owner);

			/* Insert into owner's list in sorted order */
			prev = rb_prev(&ns->ns_owner_tree_node);
			if (!prev)
				list_add_rcu(&ns->ns_owner_entry, &owner->ns_owner);
			else
				list_add_rcu(&ns->ns_owner_entry, &node_to_ns_owner(prev)->ns_owner_entry);
		} else {
			/* Only the initial user namespace doesn't have an owner. */
			VFS_WARN_ON_ONCE(ns != to_ns_common(&init_user_ns));
		}
	}
	write_sequnlock(&ns_tree_lock);

	VFS_WARN_ON_ONCE(node);

	/*
	 * Take an active reference on the owner namespace. This ensures
	 * that the owner remains visible while any of its child namespaces
	 * are active. For init namespaces this is a no-op as ns_owner()
	 * returns NULL for namespaces owned by init_user_ns.
	 */
	__ns_ref_active_get_owner(ns);
}

void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree)
{
	const struct proc_ns_operations *ops = ns->ops;
	struct user_namespace *user_ns;

	VFS_WARN_ON_ONCE(RB_EMPTY_NODE(&ns->ns_tree_node));
	VFS_WARN_ON_ONCE(list_empty(&ns->ns_list_node));
	VFS_WARN_ON_ONCE(ns->ns_type != ns_tree->type);

	write_seqlock(&ns_tree_lock);
	rb_erase(&ns->ns_tree_node, &ns_tree->ns_tree);
	RB_CLEAR_NODE(&ns->ns_tree_node);

	list_bidir_del_rcu(&ns->ns_list_node);

	rb_erase(&ns->ns_unified_tree_node, &ns_unified_tree);
	RB_CLEAR_NODE(&ns->ns_unified_tree_node);

	list_bidir_del_rcu(&ns->ns_unified_list_node);

	/* Remove from owner's rbtree if this namespace has an owner */
	if (ops) {
		user_ns = ops->owner(ns);
		if (user_ns) {
			struct ns_common *owner = &user_ns->ns;
			rb_erase(&ns->ns_owner_tree_node, &owner->ns_owner_tree);
			RB_CLEAR_NODE(&ns->ns_owner_tree_node);
		}

		list_bidir_del_rcu(&ns->ns_owner_entry);
	}

	write_sequnlock(&ns_tree_lock);
}
EXPORT_SYMBOL_GPL(__ns_tree_remove);

static int ns_find(const void *key, const struct rb_node *node)
{
	const u64 ns_id = *(u64 *)key;
	const struct ns_common *ns = node_to_ns(node);

	if (ns_id < ns->ns_id)
		return -1;
	if (ns_id > ns->ns_id)
		return 1;
	return 0;
}

static int ns_find_unified(const void *key, const struct rb_node *node)
{
	const u64 ns_id = *(u64 *)key;
	const struct ns_common *ns = node_to_ns_unified(node);

	if (ns_id < ns->ns_id)
		return -1;
	if (ns_id > ns->ns_id)
		return 1;
	return 0;
}

static struct ns_tree *ns_tree_from_type(int ns_type)
{
	switch (ns_type) {
	case CLONE_NEWCGROUP:
		return &cgroup_ns_tree;
	case CLONE_NEWIPC:
		return &ipc_ns_tree;
	case CLONE_NEWNS:
		return &mnt_ns_tree;
	case CLONE_NEWNET:
		return &net_ns_tree;
	case CLONE_NEWPID:
		return &pid_ns_tree;
	case CLONE_NEWUSER:
		return &user_ns_tree;
	case CLONE_NEWUTS:
		return &uts_ns_tree;
	case CLONE_NEWTIME:
		return &time_ns_tree;
	}

	return NULL;
}

static struct ns_common *__ns_unified_tree_lookup_rcu(u64 ns_id)
{
	struct rb_node *node;
	unsigned int seq;

	do {
		seq = read_seqbegin(&ns_tree_lock);
		node = rb_find_rcu(&ns_id, &ns_unified_tree, ns_find_unified);
		if (node)
			break;
	} while (read_seqretry(&ns_tree_lock, seq));

	return node_to_ns_unified(node);
}

static struct ns_common *__ns_tree_lookup_rcu(u64 ns_id, int ns_type)
{
	struct ns_tree *ns_tree;
	struct rb_node *node;
	unsigned int seq;

	ns_tree = ns_tree_from_type(ns_type);
	if (!ns_tree)
		return NULL;

	do {
		seq = read_seqbegin(&ns_tree_lock);
		node = rb_find_rcu(&ns_id, &ns_tree->ns_tree, ns_find);
		if (node)
			break;
	} while (read_seqretry(&ns_tree_lock, seq));

	return node_to_ns(node);
}

struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type)
{
	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious ns_tree_lookup_rcu() usage");

	if (ns_type)
		return __ns_tree_lookup_rcu(ns_id, ns_type);

	return __ns_unified_tree_lookup_rcu(ns_id);
}

/**
 * ns_tree_adjoined_rcu - find the next/previous namespace in the same
 * tree
 * @ns: namespace to start from
 * @previous: if true find the previous namespace, otherwise the next
 *
 * Find the next or previous namespace in the same tree as @ns. If
 * there is no next/previous namespace, -ENOENT is returned.
 */
struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns,
					 struct ns_tree *ns_tree, bool previous)
{
	struct list_head *list;

	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious ns_tree_adjoined_rcu() usage");

	if (previous)
		list = rcu_dereference(list_bidir_prev_rcu(&ns->ns_list_node));
	else
		list = rcu_dereference(list_next_rcu(&ns->ns_list_node));
	if (list_is_head(list, &ns_tree->ns_list))
		return ERR_PTR(-ENOENT);

	VFS_WARN_ON_ONCE(list_entry_rcu(list, struct ns_common, ns_list_node)->ns_type != ns_tree->type);

	return list_entry_rcu(list, struct ns_common, ns_list_node);
}

/**
 * ns_tree_gen_id - generate a new namespace id
 * @ns: namespace to generate id for
 * @id: if non-zero, this is the initial namespace and this is a fixed id
 *
 * Generates a new namespace id and assigns it to the namespace. All
 * namespaces types share the same id space and thus can be compared
 * directly. IOW, when two ids of two namespace are equal, they are
 * identical.
 */
u64 __ns_tree_gen_id(struct ns_common *ns, u64 id)
{
	static atomic64_t namespace_cookie = ATOMIC64_INIT(NS_LAST_INIT_ID + 1);

	if (id)
		ns->ns_id = id;
	else
		ns->ns_id = atomic64_inc_return(&namespace_cookie);
	return ns->ns_id;
}