[PATCH RFC DRAFT 14/50] ns: maintain list of owned namespaces

[Christian Brauner <brauner@kernel.org>]

The namespace tree doesn't express the ownership concept of namespace
appropriately. Maintain a list of directly owned namespaces per user
namespace. This will allow userspace and the kernel to use the listns()
system call to walk the namespace tree by owning user namespace.
Read-only list operations are completely lockless.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c            |  2 ++
 include/linux/ns_common.h |  4 ++++
 init/version-timestamp.c  |  2 ++
 ipc/msgutil.c             |  2 ++
 kernel/cgroup/cgroup.c    |  2 ++
 kernel/nscommon.c         |  2 ++
 kernel/nstree.c           | 19 +++++++++++++++++++
 kernel/pid.c              |  2 ++
 kernel/time/namespace.c   |  2 ++
 kernel/user.c             |  2 ++
 10 files changed, 39 insertions(+)

diff --git a/fs/namespace.c b/fs/namespace.c
index 5d8a80e1e944..d460ca79f0e7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5996,6 +5996,8 @@ struct mnt_namespace init_mnt_ns = {
 	.mounts		= RB_ROOT,
 	.poll		= __WAIT_QUEUE_HEAD_INITIALIZER(init_mnt_ns.poll),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_mnt_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_mnt_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_mnt_ns.ns.ns_owner),
 };
 
 static void __init init_mount_tree(void)
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index ad65005d3371..1afeaa93d319 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -123,6 +123,10 @@ struct ns_common {
 				struct rb_node ns_tree_node;
 				struct list_head ns_list_node;
 			};
+			struct /* namespace ownership list */ {
+				struct list_head ns_owner; /* list of namespaces owned by this namespace */
+				struct list_head ns_owner_entry; /* node in the owner namespace's ns_owned list */
+			};
 			atomic_t __ns_ref_active; /* do not use directly */
 		};
 		struct rcu_head ns_rcu;
diff --git a/init/version-timestamp.c b/init/version-timestamp.c
index c38498f94646..e5c278dabecf 100644
--- a/init/version-timestamp.c
+++ b/init/version-timestamp.c
@@ -22,6 +22,8 @@ struct uts_namespace init_uts_ns = {
 	.user_ns = &init_user_ns,
 	.ns.inum = ns_init_inum(&init_uts_ns),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_uts_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_uts_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_uts_ns.ns.ns_owner),
 #ifdef CONFIG_UTS_NS
 	.ns.ops = &utsns_operations,
 #endif
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index d7c66b430470..ce1de73725c0 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -32,6 +32,8 @@ struct ipc_namespace init_ipc_ns = {
 	.user_ns = &init_user_ns,
 	.ns.inum = ns_init_inum(&init_ipc_ns),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_ipc_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_ipc_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_ipc_ns.ns.ns_owner),
 #ifdef CONFIG_IPC_NS
 	.ns.ops = &ipcns_operations,
 #endif
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a18ec090ad7e..41a1fc562ed0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -258,6 +258,8 @@ struct cgroup_namespace init_cgroup_ns = {
 	.root_cset	= &init_css_set,
 	.ns.ns_type	= ns_common_type(&init_cgroup_ns),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_cgroup_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_cgroup_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_cgroup_ns.ns.ns_owner),
 };
 
 static struct file_system_type cgroup2_fs_type;
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index c97a7bbb7d76..0ef2939daf33 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -63,6 +63,8 @@ int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_ope
 	RB_CLEAR_NODE(&ns->ns_tree_node);
 	RB_CLEAR_NODE(&ns->ns_unified_tree_node);
 	INIT_LIST_HEAD(&ns->ns_list_node);
+	INIT_LIST_HEAD(&ns->ns_owner);
+	INIT_LIST_HEAD(&ns->ns_owner_entry);
 
 #ifdef CONFIG_DEBUG_VFS
 	ns_debug(ns, ops);
diff --git a/kernel/nstree.c b/kernel/nstree.c
index de5ceda44637..829682bb04a1 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -3,6 +3,7 @@
 #include <linux/nstree.h>
 #include <linux/proc_ns.h>
 #include <linux/vfsdebug.h>
+#include <linux/user_namespace.h>
 
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(ns_tree_lock);
 static struct rb_root ns_unified_tree = RB_ROOT; /* protected by ns_tree_lock */
@@ -113,8 +114,10 @@ static inline int ns_cmp_unified(struct rb_node *a, const struct rb_node *b)
 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);
 
@@ -132,6 +135,21 @@ void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree)
 		list_add_rcu(&ns->ns_list_node, &node_to_ns(prev)->ns_list_node);
 
 	rb_find_add_rcu(&ns->ns_unified_tree_node, &ns_unified_tree, ns_cmp_unified);
+
+	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);
+			list_add_tail_rcu(&ns->ns_owner_entry, &owner->ns_owner);
+		} 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);
@@ -148,6 +166,7 @@ void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree)
 	rb_erase(&ns->ns_unified_tree_node, &ns_unified_tree);
 	list_bidir_del_rcu(&ns->ns_list_node);
 	RB_CLEAR_NODE(&ns->ns_tree_node);
+	list_bidir_del_rcu(&ns->ns_owner_entry);
 	write_sequnlock(&ns_tree_lock);
 }
 EXPORT_SYMBOL_GPL(__ns_tree_remove);
diff --git a/kernel/pid.c b/kernel/pid.c
index 4f7b5054e23d..f82dab348540 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -80,6 +80,8 @@ struct pid_namespace init_pid_ns = {
 	.user_ns = &init_user_ns,
 	.ns.inum = ns_init_inum(&init_pid_ns),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_pid_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_pid_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_pid_ns.ns.ns_owner),
 #ifdef CONFIG_PID_NS
 	.ns.ops = &pidns_operations,
 #endif
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 2e7c110bd13f..15cb74267c75 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -485,6 +485,8 @@ struct time_namespace init_time_ns = {
 	.user_ns	= &init_user_ns,
 	.ns.inum	= ns_init_inum(&init_time_ns),
 	.ns.ops		= &timens_operations,
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_time_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_time_ns.ns.ns_owner),
 	.frozen_offsets	= true,
 	.ns.ns_list_node = LIST_HEAD_INIT(init_time_ns.ns.ns_list_node),
 };
diff --git a/kernel/user.c b/kernel/user.c
index bf60532856db..e392768ccd44 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -72,6 +72,8 @@ struct user_namespace init_user_ns = {
 	.group = GLOBAL_ROOT_GID,
 	.ns.inum = ns_init_inum(&init_user_ns),
 	.ns.ns_list_node = LIST_HEAD_INIT(init_user_ns.ns.ns_list_node),
+	.ns.ns_owner_entry = LIST_HEAD_INIT(init_user_ns.ns.ns_owner_entry),
+	.ns.ns_owner = LIST_HEAD_INIT(init_user_ns.ns.ns_owner),
 #ifdef CONFIG_USER_NS
 	.ns.ops = &userns_operations,
 #endif

-- 
2.47.3