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, 115 insertions, 118 deletions

diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index f5b68b8abb54..825f5865bfc5 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -2,122 +2,44 @@
 #ifndef _LINUX_NS_COMMON_H
 #define _LINUX_NS_COMMON_H
 
+#include <linux/ns/ns_common_types.h>
 #include <linux/refcount.h>
-#include <linux/rbtree.h>
+#include <linux/vfsdebug.h>
 #include <uapi/linux/sched.h>
+#include <uapi/linux/nsfs.h>
 
-struct proc_ns_operations;
-
-struct cgroup_namespace;
-struct ipc_namespace;
-struct mnt_namespace;
-struct net;
-struct pid_namespace;
-struct time_namespace;
-struct user_namespace;
-struct uts_namespace;
-
-extern struct cgroup_namespace init_cgroup_ns;
-extern struct ipc_namespace init_ipc_ns;
-extern struct mnt_namespace init_mnt_ns;
-extern struct net init_net;
-extern struct pid_namespace init_pid_ns;
-extern struct time_namespace init_time_ns;
-extern struct user_namespace init_user_ns;
-extern struct uts_namespace init_uts_ns;
-
-extern const struct proc_ns_operations netns_operations;
-extern const struct proc_ns_operations utsns_operations;
-extern const struct proc_ns_operations ipcns_operations;
-extern const struct proc_ns_operations pidns_operations;
-extern const struct proc_ns_operations pidns_for_children_operations;
-extern const struct proc_ns_operations userns_operations;
-extern const struct proc_ns_operations mntns_operations;
-extern const struct proc_ns_operations cgroupns_operations;
-extern const struct proc_ns_operations timens_operations;
-extern const struct proc_ns_operations timens_for_children_operations;
-
-struct ns_common {
-	u32 ns_type;
-	struct dentry *stashed;
-	const struct proc_ns_operations *ops;
-	unsigned int inum;
-	refcount_t __ns_ref; /* do not use directly */
-	union {
-		struct {
-			u64 ns_id;
-			struct rb_node ns_tree_node;
-			struct list_head ns_list_node;
-		};
-		struct rcu_head ns_rcu;
-	};
-};
-
+bool is_current_namespace(struct ns_common *ns);
 int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum);
 void __ns_common_free(struct ns_common *ns);
+struct ns_common *__must_check ns_owner(struct ns_common *ns);
+
+static __always_inline bool is_ns_init_inum(const struct ns_common *ns)
+{
+	VFS_WARN_ON_ONCE(ns->inum == 0);
+	return unlikely(in_range(ns->inum, MNT_NS_INIT_INO,
+				 IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1));
+}
+
+static __always_inline bool is_ns_init_id(const struct ns_common *ns)
+{
+	VFS_WARN_ON_ONCE(ns->ns_id == 0);
+	return ns->ns_id <= NS_LAST_INIT_ID;
+}
 
-#define to_ns_common(__ns)                                    \
-	_Generic((__ns),                                      \
-		struct cgroup_namespace *:       &(__ns)->ns, \
-		const struct cgroup_namespace *: &(__ns)->ns, \
-		struct ipc_namespace *:          &(__ns)->ns, \
-		const struct ipc_namespace *:    &(__ns)->ns, \
-		struct mnt_namespace *:          &(__ns)->ns, \
-		const struct mnt_namespace *:    &(__ns)->ns, \
-		struct net *:                    &(__ns)->ns, \
-		const struct net *:              &(__ns)->ns, \
-		struct pid_namespace *:          &(__ns)->ns, \
-		const struct pid_namespace *:    &(__ns)->ns, \
-		struct time_namespace *:         &(__ns)->ns, \
-		const struct time_namespace *:   &(__ns)->ns, \
-		struct user_namespace *:         &(__ns)->ns, \
-		const struct user_namespace *:   &(__ns)->ns, \
-		struct uts_namespace *:          &(__ns)->ns, \
-		const struct uts_namespace *:    &(__ns)->ns)
-
-#define ns_init_inum(__ns)                                     \
-	_Generic((__ns),                                       \
-		struct cgroup_namespace *: CGROUP_NS_INIT_INO, \
-		struct ipc_namespace *:    IPC_NS_INIT_INO,    \
-		struct mnt_namespace *:    MNT_NS_INIT_INO,    \
-		struct net *:              NET_NS_INIT_INO,    \
-		struct pid_namespace *:    PID_NS_INIT_INO,    \
-		struct time_namespace *:   TIME_NS_INIT_INO,   \
-		struct user_namespace *:   USER_NS_INIT_INO,   \
-		struct uts_namespace *:    UTS_NS_INIT_INO)
-
-#define ns_init_ns(__ns)                                    \
-	_Generic((__ns),                                    \
-		struct cgroup_namespace *: &init_cgroup_ns, \
-		struct ipc_namespace *:    &init_ipc_ns,    \
-		struct mnt_namespace *:    &init_mnt_ns,     \
-		struct net *:              &init_net,       \
-		struct pid_namespace *:    &init_pid_ns,    \
-		struct time_namespace *:   &init_time_ns,   \
-		struct user_namespace *:   &init_user_ns,   \
-		struct uts_namespace *:    &init_uts_ns)
-
-#define to_ns_operations(__ns)                                                                         \
-	_Generic((__ns),                                                                               \
-		struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \
-		struct ipc_namespace *:    (IS_ENABLED(CONFIG_IPC_NS)  ? &ipcns_operations    : NULL), \
-		struct mnt_namespace *:    &mntns_operations,                                          \
-		struct net *:              (IS_ENABLED(CONFIG_NET_NS)  ? &netns_operations    : NULL), \
-		struct pid_namespace *:    (IS_ENABLED(CONFIG_PID_NS)  ? &pidns_operations    : NULL), \
-		struct time_namespace *:   (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations   : NULL), \
-		struct user_namespace *:   (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations   : NULL), \
-		struct uts_namespace *:    (IS_ENABLED(CONFIG_UTS_NS)  ? &utsns_operations    : NULL))
-
-#define ns_common_type(__ns)                                \
-	_Generic((__ns),                                    \
-		struct cgroup_namespace *: CLONE_NEWCGROUP, \
-		struct ipc_namespace *:    CLONE_NEWIPC,    \
-		struct mnt_namespace *:    CLONE_NEWNS,     \
-		struct net *:              CLONE_NEWNET,    \
-		struct pid_namespace *:    CLONE_NEWPID,    \
-		struct time_namespace *:   CLONE_NEWTIME,   \
-		struct user_namespace *:   CLONE_NEWUSER,   \
-		struct uts_namespace *:    CLONE_NEWUTS)
+#define NS_COMMON_INIT(nsname)										\
+{													\
+	.ns_type			= ns_common_type(&nsname),					\
+	.ns_id				= ns_init_id(&nsname),						\
+	.inum				= ns_init_inum(&nsname),					\
+	.ops				= to_ns_operations(&nsname),					\
+	.stashed			= NULL,								\
+	.__ns_ref			= REFCOUNT_INIT(1),						\
+	.__ns_ref_active		= ATOMIC_INIT(1),						\
+	.ns_unified_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry),	\
+	.ns_tree_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry),		\
+	.ns_owner_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry),	\
+	.ns_owner_root.ns_list_head	= LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head),		\
+}
 
 #define ns_common_init(__ns)                     \
 	__ns_common_init(to_ns_common(__ns),     \
@@ -133,21 +55,96 @@ void __ns_common_free(struct ns_common *ns);
 
 #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
 
+static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns)
+{
+	return atomic_read(&ns->__ns_ref_active);
+}
+
+static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns)
+{
+	return refcount_read(&ns->__ns_ref);
+}
+
 static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns)
 {
-	return refcount_dec_and_test(&ns->__ns_ref);
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return false;
+	}
+	if (refcount_dec_and_test(&ns->__ns_ref)) {
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns));
+		return true;
+	}
+	return false;
 }
 
 static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns)
 {
-	return refcount_inc_not_zero(&ns->__ns_ref);
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return true;
+	}
+	if (refcount_inc_not_zero(&ns->__ns_ref))
+		return true;
+	VFS_WARN_ON_ONCE(__ns_ref_active_read(ns));
+	return false;
 }
 
-#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref)
-#define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref)
-#define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns)))
-#define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns)))
-#define ns_ref_put_and_lock(__ns, __lock) \
-	refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock))
+static __always_inline void __ns_ref_inc(struct ns_common *ns)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return;
+	}
+	refcount_inc(&ns->__ns_ref);
+}
+
+static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns,
+							       spinlock_t *ns_lock)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return false;
+	}
+	return refcount_dec_and_lock(&ns->__ns_ref, ns_lock);
+}
+
+#define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns)))
+#define ns_ref_inc(__ns) \
+	do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0)
+#define ns_ref_get(__ns) \
+	((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false)
+#define ns_ref_put(__ns) \
+	((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false)
+#define ns_ref_put_and_lock(__ns, __ns_lock) \
+	((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false)
+
+#define ns_ref_active_read(__ns) \
+	((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0)
+
+void __ns_ref_active_put(struct ns_common *ns);
+
+#define ns_ref_active_put(__ns) \
+	do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0)
+
+static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns)
+{
+	if (!__ns_ref_active_read(ns)) {
+		VFS_WARN_ON_ONCE(is_ns_init_id(ns));
+		return NULL;
+	}
+	if (!__ns_ref_get(ns))
+		return NULL;
+	return ns;
+}
+
+void __ns_ref_active_get(struct ns_common *ns);
+
+#define ns_ref_active_get(__ns) \
+	do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0)
 
 #endif