Merge patch series "ns: support file handles"

Christian Brauner <brauner@kernel.org> says:

For a while now we have supported file handles for pidfds. This has
proven to be very useful.

Extend the concept to cover namespaces as well. After this patchset it
is possible to encode and decode namespace file handles using the
commong name_to_handle_at() and open_by_handle_at() apis.

Namespaces file descriptors can already be derived from pidfds which
means they aren't subject to overmount protection bugs. IOW, it's
irrelevant if the caller would not have access to an appropriate
/proc/<pid>/ns/ directory as they could always just derive the namespace
based on a pidfd already.

It has the same advantage as pidfds. It's possible to reliably and for
the lifetime of the system refer to a namespace without pinning any
resources and to compare them.

Permission checking is kept simple. If the caller is located in the
namespace the file handle refers to they are able to open it otherwise
they must hold privilege over the owning namespace of the relevant
namespace.

Both the network namespace and the mount namespace already have an
associated cookie that isn't recycled and is fully exposed to userspace.
Move this into ns_common and use the same id space for all namespaces so
they can trivially and reliably be compared.

There's more coming based on the iterator infrastructure but the series
is large enough and focuses on file handles.

Extensive selftests included.

* patches from https://lore.kernel.org/20250912-work-namespace-v2-0-1a247645cef5@kernel.org: (33 commits)
  selftests/namespaces: add file handle selftests
  selftests/namespaces: add identifier selftests
  tools: update nsfs.h uapi header
  nsfs: add missing id retrieval support
  nsfs: support exhaustive file handles
  nsfs: support file handles
  nsfs: add current_in_namespace()
  ns: add to_<type>_ns() to respective headers
  uts: support ns lookup
  user: support ns lookup
  time: support ns lookup
  pid: support ns lookup
  net: support ns lookup
  ipc: support ns lookup
  cgroup: support ns lookup
  mnt: support ns lookup
  nstree: make iterator generic
  ns: remove ns_alloc_inum()
  uts: use ns_common_init()
  user: use ns_common_init()
  ...

Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 8 insertions, 9 deletions

diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 682f40d5632d..cfb0e28f2779 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,6 +21,7 @@
 #include <linux/fs_struct.h>
 #include <linux/bsearch.h>
 #include <linux/sort.h>
+#include <linux/nstree.h>
 
 static struct kmem_cache *user_ns_cachep __ro_after_init;
 static DEFINE_MUTEX(userns_state_mutex);
@@ -124,12 +125,11 @@ int create_user_ns(struct cred *new)
 		goto fail_dec;
 
 	ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
-	ret = ns_alloc_inum(&ns->ns);
+
+	ret = ns_common_init(&ns->ns, &userns_operations, true);
 	if (ret)
 		goto fail_free;
-	ns->ns.ops = &userns_operations;
 
-	refcount_set(&ns->ns.count, 1);
 	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
 	ns->level = parent_ns->level + 1;
@@ -159,6 +159,7 @@ int create_user_ns(struct cred *new)
 		goto fail_keyring;
 
 	set_cred_user_ns(new, ns);
+	ns_tree_add(ns);
 	return 0;
 fail_keyring:
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -201,6 +202,7 @@ static void free_user_ns(struct work_struct *work)
 	do {
 		struct ucounts *ucounts = ns->ucounts;
 		parent = ns->parent;
+		ns_tree_remove(ns);
 		if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
 			kfree(ns->gid_map.forward);
 			kfree(ns->gid_map.reverse);
@@ -219,7 +221,8 @@ static void free_user_ns(struct work_struct *work)
 		retire_userns_sysctls(ns);
 		key_free_user_ns(ns);
 		ns_free_inum(&ns->ns);
-		kmem_cache_free(user_ns_cachep, ns);
+		/* Concurrent nstree traversal depends on a grace period. */
+		kfree_rcu(ns, ns.ns_rcu);
 		dec_user_namespaces(ucounts);
 		ns = parent;
 	} while (refcount_dec_and_test(&parent->ns.count));
@@ -1322,11 +1325,6 @@ bool current_in_userns(const struct user_namespace *target_ns)
 }
 EXPORT_SYMBOL(current_in_userns);
 
-static inline struct user_namespace *to_user_ns(struct ns_common *ns)
-{
-	return container_of(ns, struct user_namespace, ns);
-}
-
 static struct ns_common *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
@@ -1413,6 +1411,7 @@ const struct proc_ns_operations userns_operations = {
 static __init int user_namespaces_init(void)
 {
 	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT);
+	ns_tree_add(&init_user_ns);
 	return 0;
 }
 subsys_initcall(user_namespaces_init);