Merge tag 'namespace-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull namespace updates from Christian Brauner:
 "This contains substantial namespace infrastructure changes including a new
  system call, active reference counting, and extensive header cleanups.
  The branch depends on the shared kbuild branch for -fms-extensions support.

  Features:

   - listns() system call

     Add a new listns() system call that allows userspace to iterate
     through namespaces in the system. This provides a programmatic
     interface to discover and inspect namespaces, addressing
     longstanding limitations:

     Currently, there is no direct way for userspace to enumerate
     namespaces. Applications must resort to scanning /proc/*/ns/ across
     all processes, which is:
      - Inefficient - requires iterating over all processes
      - Incomplete - misses namespaces not attached to any running
        process but kept alive by file descriptors, bind mounts, or
        parent references
      - Permission-heavy - requires access to /proc for many processes
      - No ordering or ownership information
      - No filtering per namespace type

     The listns() system call solves these problems:

       ssize_t listns(const struct ns_id_req *req, u64 *ns_ids,
                      size_t nr_ns_ids, unsigned int flags);

       struct ns_id_req {
             __u32 size;
             __u32 spare;
             __u64 ns_id;
             struct /* listns */ {
                     __u32 ns_type;
                     __u32 spare2;
                     __u64 user_ns_id;
             };
       };

     Features include:
      - Pagination support for large namespace sets
      - Filtering by namespace type (MNT_NS, NET_NS, USER_NS, etc.)
      - Filtering by owning user namespace
      - Permission checks respecting namespace isolation

   - Active Reference Counting

     Introduce an active reference count that tracks namespace
     visibility to userspace. A namespace is visible in the following
     cases:
      - The namespace is in use by a task
      - The namespace is persisted through a VFS object (namespace file
        descriptor or bind-mount)
      - The namespace is a hierarchical type and is the parent of child
        namespaces

     The active reference count does not regulate lifetime (that's still
     done by the normal reference count) - it only regulates visibility
     to namespace file handles and listns().

     This prevents resurrection of namespaces that are pinned only for
     internal kernel reasons (e.g., user namespaces held by
     file->f_cred, lazy TLB references on idle CPUs, etc.) which should
     not be accessible via (1)-(3).

   - Unified Namespace Tree

     Introduce a unified tree structure for all namespaces with:
      - Fixed IDs assigned to initial namespaces
      - Lookup based solely on inode number
      - Maintained list of owned namespaces per user namespace
      - Simplified rbtree comparison helpers

   Cleanups

    - Header Reorganization:
      - Move namespace types into separate header (ns_common_types.h)
      - Decouple nstree from ns_common header
      - Move nstree types into separate header
      - Switch to new ns_tree_{node,root} structures with helper functions
      - Use guards for ns_tree_lock

   - Initial Namespace Reference Count Optimization
      - Make all reference counts on initial namespaces a nop to avoid
        pointless cacheline ping-pong for namespaces that can never go
        away
      - Drop custom reference count initialization for initial namespaces
      - Add NS_COMMON_INIT() macro and use it for all namespaces
      - pid: rely on common reference count behavior

   - Miscellaneous Cleanups
      - Rename exit_task_namespaces() to exit_nsproxy_namespaces()
      - Rename is_initial_namespace() and make argument const
      - Use boolean to indicate anonymous mount namespace
      - Simplify owner list iteration in nstree
      - nsfs: raise SB_I_NODEV, SB_I_NOEXEC, and DCACHE_DONTCACHE explicitly
      - nsfs: use inode_just_drop()
      - pidfs: raise DCACHE_DONTCACHE explicitly
      - pidfs: simplify PIDFD_GET__NAMESPACE ioctls
      - libfs: allow to specify s_d_flags
      - cgroup: add cgroup namespace to tree after owner is set
      - nsproxy: fix free_nsproxy() and simplify create_new_namespaces()

  Fixes:

   - setns(pidfd, ...) race condition

     Fix a subtle race when using pidfds with setns(). When the target
     task exits after prepare_nsset() but before commit_nsset(), the
     namespace's active reference count might have been dropped. If
     setns() then installs the namespaces, it would bump the active
     reference count from zero without taking the required reference on
     the owner namespace, leading to underflow when later decremented.

     The fix resurrects the ownership chain if necessary - if the caller
     succeeded in grabbing passive references, the setns() should
     succeed even if the target task exits or gets reaped.

   - Return EFAULT on put_user() error instead of success

   - Make sure references are dropped outside of RCU lock (some
     namespaces like mount namespace sleep when putting the last
     reference)

   - Don't skip active reference count initialization for network
     namespace

   - Add asserts for active refcount underflow

   - Add asserts for initial namespace reference counts (both passive
     and active)

   - ipc: enable is_ns_init_id() assertions

   - Fix kernel-doc comments for internal nstree functions

   - Selftests
      - 15 active reference count tests
      - 9 listns() functionality tests
      - 7 listns() permission tests
      - 12 inactive namespace resurrection tests
      - 3 threaded active reference count tests
      - commit_creds() active reference tests
      - Pagination and stress tests
      - EFAULT handling test
      - nsid tests fixes"

* tag 'namespace-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (103 commits)
  pidfs: simplify PIDFD_GET_<type>_NAMESPACE ioctls
  nstree: fix kernel-doc comments for internal functions
  nsproxy: fix free_nsproxy() and simplify create_new_namespaces()
  selftests/namespaces: fix nsid tests
  ns: drop custom reference count initialization for initial namespaces
  pid: rely on common reference count behavior
  ns: add asserts for initial namespace active reference counts
  ns: add asserts for initial namespace reference counts
  ns: make all reference counts on initial namespace a nop
  ipc: enable is_ns_init_id() assertions
  fs: use boolean to indicate anonymous mount namespace
  ns: rename is_initial_namespace()
  ns: make is_initial_namespace() argument const
  nstree: use guards for ns_tree_lock
  nstree: simplify owner list iteration
  nstree: switch to new structures
  nstree: add helper to operate on struct ns_tree_{node,root}
  nstree: move nstree types into separate header
  nstree: decouple from ns_common header
  ns: move namespace types into separate header
  ...

1 files changed, 35 insertions, 17 deletions

diff --git a/include/linux/nstree.h b/include/linux/nstree.h
index 8b8636690473..175e4625bfa6 100644
--- a/include/linux/nstree.h
+++ b/include/linux/nstree.h
@@ -1,22 +1,34 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
 #ifndef _LINUX_NSTREE_H
 #define _LINUX_NSTREE_H
 
-#include <linux/ns_common.h>
+#include <linux/ns/nstree_types.h>
 #include <linux/nsproxy.h>
 #include <linux/rbtree.h>
 #include <linux/seqlock.h>
 #include <linux/rculist.h>
 #include <linux/cookie.h>
+#include <uapi/linux/nsfs.h>
 
-extern struct ns_tree cgroup_ns_tree;
-extern struct ns_tree ipc_ns_tree;
-extern struct ns_tree mnt_ns_tree;
-extern struct ns_tree net_ns_tree;
-extern struct ns_tree pid_ns_tree;
-extern struct ns_tree time_ns_tree;
-extern struct ns_tree user_ns_tree;
-extern struct ns_tree uts_ns_tree;
+struct ns_common;
+
+extern struct ns_tree_root cgroup_ns_tree;
+extern struct ns_tree_root ipc_ns_tree;
+extern struct ns_tree_root mnt_ns_tree;
+extern struct ns_tree_root net_ns_tree;
+extern struct ns_tree_root pid_ns_tree;
+extern struct ns_tree_root time_ns_tree;
+extern struct ns_tree_root user_ns_tree;
+extern struct ns_tree_root uts_ns_tree;
+
+void ns_tree_node_init(struct ns_tree_node *node);
+void ns_tree_root_init(struct ns_tree_root *root);
+bool ns_tree_node_empty(const struct ns_tree_node *node);
+struct rb_node *ns_tree_node_add(struct ns_tree_node *node,
+				  struct ns_tree_root *root,
+				  int (*cmp)(struct rb_node *, const struct rb_node *));
+void ns_tree_node_del(struct ns_tree_node *node, struct ns_tree_root *root);
 
 #define to_ns_tree(__ns)					\
 	_Generic((__ns),					\
@@ -29,17 +41,21 @@ extern struct ns_tree uts_ns_tree;
 		struct user_namespace *:   &(user_ns_tree),	\
 		struct uts_namespace *:    &(uts_ns_tree))
 
-u64 ns_tree_gen_id(struct ns_common *ns);
-void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree);
-void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree);
+#define ns_tree_gen_id(__ns)                 \
+	__ns_tree_gen_id(to_ns_common(__ns), \
+			 (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0))
+
+u64 __ns_tree_gen_id(struct ns_common *ns, u64 id);
+void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree_root *ns_tree);
+void __ns_tree_remove(struct ns_common *ns, struct ns_tree_root *ns_tree);
 struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type);
 struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns,
-					 struct ns_tree *ns_tree,
+					 struct ns_tree_root *ns_tree,
 					 bool previous);
 
-static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree)
+static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree_root *ns_tree, u64 id)
 {
-	ns_tree_gen_id(ns);
+	__ns_tree_gen_id(ns, id);
 	__ns_tree_add_raw(ns, ns_tree);
 }
 
@@ -59,7 +75,9 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree)
  * This function assigns a new id to the namespace and adds it to the
  * appropriate namespace tree and list.
  */
-#define ns_tree_add(__ns) __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns))
+#define ns_tree_add(__ns)                                   \
+	__ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns), \
+		      (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0))
 
 /**
  * ns_tree_remove - Remove a namespace from a namespace tree
@@ -73,6 +91,6 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree)
 #define ns_tree_adjoined_rcu(__ns, __previous) \
 	__ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous)
 
-#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node))
+#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node.ns_node))
 
 #endif /* _LINUX_NSTREE_H */