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
  ...

12 files changed, 980 insertions, 156 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index fdee387f0d6b..2bf3951ca88f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -250,12 +250,9 @@ bool cgroup_enable_per_threadgroup_rwsem __read_mostly;
 
 /* cgroup namespace for init task */
 struct cgroup_namespace init_cgroup_ns = {
-	.ns.__ns_ref	= REFCOUNT_INIT(2),
+	.ns		= NS_COMMON_INIT(init_cgroup_ns),
 	.user_ns	= &init_user_ns,
-	.ns.ops		= &cgroupns_operations,
-	.ns.inum	= ns_init_inum(&init_cgroup_ns),
 	.root_cset	= &init_css_set,
-	.ns.ns_type	= ns_common_type(&init_cgroup_ns),
 };
 
 static struct file_system_type cgroup2_fs_type;
@@ -1522,9 +1519,9 @@ static struct cgroup *current_cgns_cgroup_dfl(void)
 	} else {
 		/*
 		 * NOTE: This function may be called from bpf_cgroup_from_id()
-		 * on a task which has already passed exit_task_namespaces() and
-		 * nsproxy == NULL. Fall back to cgrp_dfl_root which will make all
-		 * cgroups visible for lookups.
+		 * on a task which has already passed exit_nsproxy_namespaces()
+		 * and nsproxy == NULL. Fall back to cgrp_dfl_root which will
+		 * make all cgroups visible for lookups.
 		 */
 		return &cgrp_dfl_root.cgrp;
 	}
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index fdbe57578e68..db9617556dd7 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -30,7 +30,6 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
 	ret = ns_common_init(new_ns);
 	if (ret)
 		return ERR_PTR(ret);
-	ns_tree_add(new_ns);
 	return no_free_ptr(new_ns);
 }
 
@@ -86,6 +85,7 @@ struct cgroup_namespace *copy_cgroup_ns(u64 flags,
 	new_ns->ucounts = ucounts;
 	new_ns->root_cset = cset;
 
+	ns_tree_add(new_ns);
 	return new_ns;
 }
 
diff --git a/kernel/cred.c b/kernel/cred.c
index dbf6b687dc5c..a6e7f580df14 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -306,6 +306,7 @@ int copy_creds(struct task_struct *p, u64 clone_flags)
 		kdebug("share_creds(%p{%ld})",
 		       p->cred, atomic_long_read(&p->cred->usage));
 		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
+		get_cred_namespaces(p);
 		return 0;
 	}
 
@@ -343,6 +344,8 @@ int copy_creds(struct task_struct *p, u64 clone_flags)
 
 	p->cred = p->real_cred = get_cred(new);
 	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
+	get_cred_namespaces(p);
+
 	return 0;
 
 error_put:
@@ -435,10 +438,13 @@ int commit_creds(struct cred *new)
 	 */
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
+
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
+	if (new->user_ns != old->user_ns)
+		switch_cred_namespaces(old, new);
 
 	/* send notifications */
 	if (!uid_eq(new->uid,   old->uid)  ||
diff --git a/kernel/exit.c b/kernel/exit.c
index 9f74e8f1c431..988e16efd66b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -291,6 +291,7 @@ repeat:
 	write_unlock_irq(&tasklist_lock);
 	/* @thread_pid can't go away until free_pids() below */
 	proc_flush_pid(thread_pid);
+	exit_cred_namespaces(p);
 	add_device_randomness(&p->se.sum_exec_runtime,
 			      sizeof(p->se.sum_exec_runtime));
 	free_pids(post.pids);
@@ -962,7 +963,7 @@ void __noreturn do_exit(long code)
 	exit_fs(tsk);
 	if (group_dead)
 		disassociate_ctty(1);
-	exit_task_namespaces(tsk);
+	exit_nsproxy_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 3da0f08615a9..f1857672426e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2453,7 +2453,7 @@ bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
 bad_fork_cleanup_namespaces:
-	exit_task_namespaces(p);
+	exit_nsproxy_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm) {
 		mm_clear_owner(p->mm, p);
@@ -2487,6 +2487,7 @@ bad_fork_cleanup_delayacct:
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
+	exit_cred_namespaces(p);
 	exit_creds(p);
 bad_fork_free:
 	WRITE_ONCE(p->__state, TASK_DEAD);
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index c1fb2bad6d72..bdc3c86231d3 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -1,7 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
 
 #include <linux/ns_common.h>
+#include <linux/nstree.h>
 #include <linux/proc_ns.h>
+#include <linux/user_namespace.h>
 #include <linux/vfsdebug.h>
 
 #ifdef CONFIG_DEBUG_VFS
@@ -52,26 +55,257 @@ static void ns_debug(struct ns_common *ns, const struct proc_ns_operations *ops)
 
 int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum)
 {
+	int ret = 0;
+
 	refcount_set(&ns->__ns_ref, 1);
 	ns->stashed = NULL;
 	ns->ops = ops;
 	ns->ns_id = 0;
 	ns->ns_type = ns_type;
-	RB_CLEAR_NODE(&ns->ns_tree_node);
-	INIT_LIST_HEAD(&ns->ns_list_node);
+	ns_tree_node_init(&ns->ns_tree_node);
+	ns_tree_node_init(&ns->ns_unified_node);
+	ns_tree_node_init(&ns->ns_owner_node);
+	ns_tree_root_init(&ns->ns_owner_root);
 
 #ifdef CONFIG_DEBUG_VFS
 	ns_debug(ns, ops);
 #endif
 
-	if (inum) {
+	if (inum)
 		ns->inum = inum;
-		return 0;
-	}
-	return proc_alloc_inum(&ns->inum);
+	else
+		ret = proc_alloc_inum(&ns->inum);
+	if (ret)
+		return ret;
+	/*
+	 * Tree ref starts at 0. It's incremented when namespace enters
+	 * active use (installed in nsproxy) and decremented when all
+	 * active uses are gone. Initial namespaces are always active.
+	 */
+	if (is_ns_init_inum(ns))
+		atomic_set(&ns->__ns_ref_active, 1);
+	else
+		atomic_set(&ns->__ns_ref_active, 0);
+	return 0;
 }
 
 void __ns_common_free(struct ns_common *ns)
 {
 	proc_free_inum(ns->inum);
 }
+
+struct ns_common *__must_check ns_owner(struct ns_common *ns)
+{
+	struct user_namespace *owner;
+
+	if (unlikely(!ns->ops))
+		return NULL;
+	VFS_WARN_ON_ONCE(!ns->ops->owner);
+	owner = ns->ops->owner(ns);
+	VFS_WARN_ON_ONCE(!owner && ns != to_ns_common(&init_user_ns));
+	if (!owner)
+		return NULL;
+	/* Skip init_user_ns as it's always active */
+	if (owner == &init_user_ns)
+		return NULL;
+	return to_ns_common(owner);
+}
+
+/*
+ * The active reference count works by having each namespace that gets
+ * created take a single active reference on its owning user namespace.
+ * That single reference is only released once the child namespace's
+ * active count itself goes down.
+ *
+ * A regular namespace tree might look as follow:
+ * Legend:
+ * + : adding active reference
+ * - : dropping active reference
+ * x : always active (initial namespace)
+ *
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        +      +
+ *                        user_ns1 (2)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        +   +   +
+ *                        user_ns2 (3)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * If both net_ns and pid_ns put their last active reference on
+ * themselves it will cascade to user_ns1 dropping its own active
+ * reference and dropping one active reference on user_ns2:
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        -      -
+ *                        user_ns1 (0)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        +   -   +
+ *                        user_ns2 (2)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * The iteration stops once we reach a namespace that still has active
+ * references.
+ */
+void __ns_ref_active_put(struct ns_common *ns)
+{
+	/* Initial namespaces are always active. */
+	if (is_ns_init_id(ns))
+		return;
+
+	if (!atomic_dec_and_test(&ns->__ns_ref_active)) {
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) < 0);
+		return;
+	}
+
+	VFS_WARN_ON_ONCE(is_ns_init_id(ns));
+	VFS_WARN_ON_ONCE(!__ns_ref_read(ns));
+
+	for (;;) {
+		ns = ns_owner(ns);
+		if (!ns)
+			return;
+		VFS_WARN_ON_ONCE(is_ns_init_id(ns));
+		if (!atomic_dec_and_test(&ns->__ns_ref_active)) {
+			VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) < 0);
+			return;
+		}
+	}
+}
+
+/*
+ * The active reference count works by having each namespace that gets
+ * created take a single active reference on its owning user namespace.
+ * That single reference is only released once the child namespace's
+ * active count itself goes down. This makes it possible to efficiently
+ * resurrect a namespace tree:
+ *
+ * A regular namespace tree might look as follow:
+ * Legend:
+ * + : adding active reference
+ * - : dropping active reference
+ * x : always active (initial namespace)
+ *
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        +      +
+ *                        user_ns1 (2)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        +   +   +
+ *                        user_ns2 (3)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * If both net_ns and pid_ns put their last active reference on
+ * themselves it will cascade to user_ns1 dropping its own active
+ * reference and dropping one active reference on user_ns2:
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        -      -
+ *                        user_ns1 (0)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        +   -   +
+ *                        user_ns2 (2)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * Assume the whole tree is dead but all namespaces are still active:
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        -      -
+ *                        user_ns1 (0)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        -   -   -
+ *                        user_ns2 (0)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * Now assume the net_ns gets resurrected (.e.g., via the SIOCGSKNS ioctl()):
+ *
+ *                 net_ns          pid_ns
+ *                       \        /
+ *                        +      -
+ *                        user_ns1 (0)
+ *                            |
+ *                 ipc_ns     |     uts_ns
+ *                       \    |    /
+ *                        -   +   -
+ *                        user_ns2 (0)
+ *                            |
+ *            cgroup_ns       |       mnt_ns
+ *                     \      |      /
+ *                      x     x     x
+ *                      init_user_ns (1)
+ *
+ * If net_ns had a zero reference count and we bumped it we also need to
+ * take another reference on its owning user namespace. Similarly, if
+ * pid_ns had a zero reference count it also needs to take another
+ * reference on its owning user namespace. So both net_ns and pid_ns
+ * will each have their own reference on the owning user namespace.
+ *
+ * If the owning user namespace user_ns1 had a zero reference count then
+ * it also needs to take another reference on its owning user namespace
+ * and so on.
+ */
+void __ns_ref_active_get(struct ns_common *ns)
+{
+	int prev;
+
+	/* Initial namespaces are always active. */
+	if (is_ns_init_id(ns))
+		return;
+
+	/* If we didn't resurrect the namespace we're done. */
+	prev = atomic_fetch_add(1, &ns->__ns_ref_active);
+	VFS_WARN_ON_ONCE(prev < 0);
+	if (likely(prev))
+		return;
+
+	/*
+	 * We did resurrect it. Walk the ownership hierarchy upwards
+	 * until we found an owning user namespace that is active.
+	 */
+	for (;;) {
+		ns = ns_owner(ns);
+		if (!ns)
+			return;
+
+		VFS_WARN_ON_ONCE(is_ns_init_id(ns));
+		prev = atomic_fetch_add(1, &ns->__ns_ref_active);
+		VFS_WARN_ON_ONCE(prev < 0);
+		if (likely(prev))
+			return;
+	}
+}
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 19aa64ab08c8..259c4b4f1eeb 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/cgroup.h>
 #include <linux/perf_event.h>
+#include <linux/nstree.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
@@ -59,6 +60,25 @@ static inline struct nsproxy *create_nsproxy(void)
 	return nsproxy;
 }
 
+static inline void nsproxy_free(struct nsproxy *ns)
+{
+	put_mnt_ns(ns->mnt_ns);
+	put_uts_ns(ns->uts_ns);
+	put_ipc_ns(ns->ipc_ns);
+	put_pid_ns(ns->pid_ns_for_children);
+	put_time_ns(ns->time_ns);
+	put_time_ns(ns->time_ns_for_children);
+	put_cgroup_ns(ns->cgroup_ns);
+	put_net(ns->net_ns);
+	kmem_cache_free(nsproxy_cachep, ns);
+}
+
+void deactivate_nsproxy(struct nsproxy *ns)
+{
+	nsproxy_ns_active_put(ns);
+	nsproxy_free(ns);
+}
+
 /*
  * Create new nsproxy and all of its the associated namespaces.
  * Return the newly created nsproxy.  Do not attach this to the task,
@@ -179,23 +199,11 @@ int copy_namespaces(u64 flags, struct task_struct *tsk)
 	if ((flags & CLONE_VM) == 0)
 		timens_on_fork(new_ns, tsk);
 
+	nsproxy_ns_active_get(new_ns);
 	tsk->nsproxy = new_ns;
 	return 0;
 }
 
-void free_nsproxy(struct nsproxy *ns)
-{
-	put_mnt_ns(ns->mnt_ns);
-	put_uts_ns(ns->uts_ns);
-	put_ipc_ns(ns->ipc_ns);
-	put_pid_ns(ns->pid_ns_for_children);
-	put_time_ns(ns->time_ns);
-	put_time_ns(ns->time_ns_for_children);
-	put_cgroup_ns(ns->cgroup_ns);
-	put_net(ns->net_ns);
-	kmem_cache_free(nsproxy_cachep, ns);
-}
-
 /*
  * Called from unshare. Unshare all the namespaces part of nsproxy.
  * On success, returns the new nsproxy.
@@ -232,6 +240,9 @@ void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
 
 	might_sleep();
 
+	if (new)
+		nsproxy_ns_active_get(new);
+
 	task_lock(p);
 	ns = p->nsproxy;
 	p->nsproxy = new;
@@ -241,11 +252,27 @@ void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
 		put_nsproxy(ns);
 }
 
-void exit_task_namespaces(struct task_struct *p)
+void exit_nsproxy_namespaces(struct task_struct *p)
 {
 	switch_task_namespaces(p, NULL);
 }
 
+void switch_cred_namespaces(const struct cred *old, const struct cred *new)
+{
+	ns_ref_active_get(new->user_ns);
+	ns_ref_active_put(old->user_ns);
+}
+
+void get_cred_namespaces(struct task_struct *tsk)
+{
+	ns_ref_active_get(tsk->real_cred->user_ns);
+}
+
+void exit_cred_namespaces(struct task_struct *tsk)
+{
+	ns_ref_active_put(tsk->real_cred->user_ns);
+}
+
 int exec_task_namespaces(void)
 {
 	struct task_struct *tsk = current;
@@ -315,7 +342,7 @@ static void put_nsset(struct nsset *nsset)
 	if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS))
 		free_fs_struct(nsset->fs);
 	if (nsset->nsproxy)
-		free_nsproxy(nsset->nsproxy);
+		nsproxy_free(nsset->nsproxy);
 }
 
 static int prepare_nsset(unsigned flags, struct nsset *nsset)
diff --git a/kernel/nstree.c b/kernel/nstree.c
index b24a320a11a6..f36c59e6951d 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -1,140 +1,261 @@
 // 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/syscalls.h>
+#include <linux/user_namespace.h>
 
-/**
- * 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
- * @ns_tree_lock: Seqlock to protect the tree and list
- * @type: type of namespaces in this tree
- */
-struct ns_tree {
-       struct rb_root ns_tree;
-       struct list_head ns_list;
-       seqlock_t ns_tree_lock;
-       int type;
+static __cacheline_aligned_in_smp DEFINE_SEQLOCK(ns_tree_lock);
+
+DEFINE_LOCK_GUARD_0(ns_tree_writer,
+		    write_seqlock(&ns_tree_lock),
+		    write_sequnlock(&ns_tree_lock))
+
+DEFINE_LOCK_GUARD_0(ns_tree_locked_reader,
+		    read_seqlock_excl(&ns_tree_lock),
+		    read_sequnlock_excl(&ns_tree_lock))
+
+static struct ns_tree_root ns_unified_root = { /* protected by ns_tree_lock */
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(ns_unified_root.ns_list_head),
 };
 
-struct ns_tree mnt_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(mnt_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(mnt_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWNS,
+struct ns_tree_root mnt_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(mnt_ns_tree.ns_list_head),
 };
 
-struct ns_tree net_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(net_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(net_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWNET,
+struct ns_tree_root net_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(net_ns_tree.ns_list_head),
 };
 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),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(uts_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWUTS,
+struct ns_tree_root uts_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(uts_ns_tree.ns_list_head),
 };
 
-struct ns_tree user_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(user_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(user_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWUSER,
+struct ns_tree_root user_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(user_ns_tree.ns_list_head),
 };
 
-struct ns_tree ipc_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(ipc_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(ipc_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWIPC,
+struct ns_tree_root ipc_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(ipc_ns_tree.ns_list_head),
 };
 
-struct ns_tree pid_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(pid_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(pid_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWPID,
+struct ns_tree_root pid_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(pid_ns_tree.ns_list_head),
 };
 
-struct ns_tree cgroup_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(cgroup_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(cgroup_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWCGROUP,
+struct ns_tree_root cgroup_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(cgroup_ns_tree.ns_list_head),
 };
 
-struct ns_tree time_ns_tree = {
-	.ns_tree = RB_ROOT,
-	.ns_list = LIST_HEAD_INIT(time_ns_tree.ns_list),
-	.ns_tree_lock = __SEQLOCK_UNLOCKED(time_ns_tree.ns_tree_lock),
-	.type = CLONE_NEWTIME,
+struct ns_tree_root time_ns_tree = {
+	.ns_rb = RB_ROOT,
+	.ns_list_head = LIST_HEAD_INIT(time_ns_tree.ns_list_head),
 };
 
-DEFINE_COOKIE(namespace_cookie);
+/**
+ * ns_tree_node_init - Initialize a namespace tree node
+ * @node: The node to initialize
+ *
+ * Initializes both the rbtree node and list entry.
+ */
+void ns_tree_node_init(struct ns_tree_node *node)
+{
+	RB_CLEAR_NODE(&node->ns_node);
+	INIT_LIST_HEAD(&node->ns_list_entry);
+}
+
+/**
+ * ns_tree_root_init - Initialize a namespace tree root
+ * @root: The root to initialize
+ *
+ * Initializes both the rbtree root and list head.
+ */
+void ns_tree_root_init(struct ns_tree_root *root)
+{
+	root->ns_rb = RB_ROOT;
+	INIT_LIST_HEAD(&root->ns_list_head);
+}
+
+/**
+ * ns_tree_node_empty - Check if a namespace tree node is empty
+ * @node: The node to check
+ *
+ * Returns true if the node is not in any tree.
+ */
+bool ns_tree_node_empty(const struct ns_tree_node *node)
+{
+	return RB_EMPTY_NODE(&node->ns_node);
+}
+
+/**
+ * ns_tree_node_add - Add a node to a namespace tree
+ * @node: The node to add
+ * @root: The tree root to add to
+ * @cmp: Comparison function for rbtree insertion
+ *
+ * Adds the node to both the rbtree and the list, maintaining sorted order.
+ * The list is maintained in the same order as the rbtree to enable efficient
+ * iteration.
+ *
+ * Returns: NULL if insertion succeeded, existing node if duplicate found
+ */
+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 *))
+{
+	struct rb_node *ret, *prev;
+
+	/* Add to rbtree */
+	ret = rb_find_add_rcu(&node->ns_node, &root->ns_rb, cmp);
+
+	/* Add to list in sorted order */
+	prev = rb_prev(&node->ns_node);
+	if (!prev) {
+		/* No previous node, add at head */
+		list_add_rcu(&node->ns_list_entry, &root->ns_list_head);
+	} else {
+		/* Add after previous node */
+		struct ns_tree_node *prev_node;
+		prev_node = rb_entry(prev, struct ns_tree_node, ns_node);
+		list_add_rcu(&node->ns_list_entry, &prev_node->ns_list_entry);
+	}
+
+	return ret;
+}
+
+/**
+ * ns_tree_node_del - Remove a node from a namespace tree
+ * @node: The node to remove
+ * @root: The tree root to remove from
+ *
+ * Removes the node from both the rbtree and the list atomically.
+ */
+void ns_tree_node_del(struct ns_tree_node *node, struct ns_tree_root *root)
+{
+	rb_erase(&node->ns_node, &root->ns_rb);
+	RB_CLEAR_NODE(&node->ns_node);
+	list_bidir_del_rcu(&node->ns_list_entry);
+}
 
 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);
+	return rb_entry(node, struct ns_common, ns_tree_node.ns_node);
 }
 
-static inline int ns_cmp(struct rb_node *a, const struct rb_node *b)
+static inline struct ns_common *node_to_ns_unified(const struct rb_node *node)
 {
-	struct ns_common *ns_a = node_to_ns(a);
-	struct ns_common *ns_b = node_to_ns(b);
-	u64 ns_id_a = ns_a->ns_id;
-	u64 ns_id_b = ns_b->ns_id;
+	if (!node)
+		return NULL;
+	return rb_entry(node, struct ns_common, ns_unified_node.ns_node);
+}
 
-	if (ns_id_a < ns_id_b)
+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_node.ns_node);
+}
+
+static int ns_id_cmp(u64 id_a, u64 id_b)
+{
+	if (id_a < id_b)
 		return -1;
-	if (ns_id_a > ns_id_b)
+	if (id_a > id_b)
 		return 1;
 	return 0;
 }
 
-void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree)
+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)
 {
-	struct rb_node *node, *prev;
+	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_root *ns_tree)
+{
+	struct rb_node *node;
+	const struct proc_ns_operations *ops = ns->ops;
 
 	VFS_WARN_ON_ONCE(!ns->ns_id);
 
-	write_seqlock(&ns_tree->ns_tree_lock);
+	guard(ns_tree_writer)();
 
-	VFS_WARN_ON_ONCE(ns->ns_type != ns_tree->type);
+	/* Add to per-type tree and list */
+	node = ns_tree_node_add(&ns->ns_tree_node, ns_tree, ns_cmp);
 
-	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 */
+	ns_tree_node_add(&ns->ns_unified_node, &ns_unified_root, ns_cmp_unified);
+
+	/* Add to owner's tree if applicable */
+	if (ops) {
+		struct user_namespace *user_ns;
 
-	write_sequnlock(&ns_tree->ns_tree_lock);
+		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 tree and list */
+			ns_tree_node_add(&ns->ns_owner_node, &owner->ns_owner_root, ns_cmp_owner);
+		} else {
+			/* Only the initial user namespace doesn't have an owner. */
+			VFS_WARN_ON_ONCE(ns != to_ns_common(&init_user_ns));
+		}
+	}
 
 	VFS_WARN_ON_ONCE(node);
 }
 
-void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree)
+void __ns_tree_remove(struct ns_common *ns, struct ns_tree_root *ns_tree)
 {
-	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);
+	const struct proc_ns_operations *ops = ns->ops;
+	struct user_namespace *user_ns;
+
+	VFS_WARN_ON_ONCE(ns_tree_node_empty(&ns->ns_tree_node));
+	VFS_WARN_ON_ONCE(list_empty(&ns->ns_tree_node.ns_list_entry));
+
+	write_seqlock(&ns_tree_lock);
+
+	/* Remove from per-type tree and list */
+	ns_tree_node_del(&ns->ns_tree_node, ns_tree);
+
+	/* Remove from unified tree and list */
+	ns_tree_node_del(&ns->ns_unified_node, &ns_unified_root);
 
-	write_seqlock(&ns_tree->ns_tree_lock);
-	rb_erase(&ns->ns_tree_node, &ns_tree->ns_tree);
-	list_bidir_del_rcu(&ns->ns_list_node);
-	RB_CLEAR_NODE(&ns->ns_tree_node);
-	write_sequnlock(&ns_tree->ns_tree_lock);
+	/* Remove from owner's tree if applicable */
+	if (ops) {
+		user_ns = ops->owner(ns);
+		if (user_ns) {
+			struct ns_common *owner = &user_ns->ns;
+			ns_tree_node_del(&ns->ns_owner_node, &owner->ns_owner_root);
+		}
+	}
+
+	write_sequnlock(&ns_tree_lock);
 }
 EXPORT_SYMBOL_GPL(__ns_tree_remove);
 
@@ -150,8 +271,19 @@ static int ns_find(const void *key, const struct rb_node *node)
 	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);
 
-static struct ns_tree *ns_tree_from_type(int ns_type)
+	if (ns_id < ns->ns_id)
+		return -1;
+	if (ns_id > ns->ns_id)
+		return 1;
+	return 0;
+}
+
+static struct ns_tree_root *ns_tree_from_type(int ns_type)
 {
 	switch (ns_type) {
 	case CLONE_NEWCGROUP:
@@ -175,73 +307,507 @@ static struct ns_tree *ns_tree_from_type(int ns_type)
 	return NULL;
 }
 
-struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type)
+static struct ns_common *__ns_unified_tree_lookup_rcu(u64 ns_id)
 {
-	struct ns_tree *ns_tree;
 	struct rb_node *node;
 	unsigned int seq;
 
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious ns_tree_lookup_rcu() usage");
+	do {
+		seq = read_seqbegin(&ns_tree_lock);
+		node = rb_find_rcu(&ns_id, &ns_unified_root.ns_rb, 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_root *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->ns_tree_lock);
-		node = rb_find_rcu(&ns_id, &ns_tree->ns_tree, ns_find);
+		seq = read_seqbegin(&ns_tree_lock);
+		node = rb_find_rcu(&ns_id, &ns_tree->ns_rb, ns_find);
 		if (node)
 			break;
-	} while (read_seqretry(&ns_tree->ns_tree_lock, seq));
+	} while (read_seqretry(&ns_tree_lock, seq));
 
-	if (!node)
-		return NULL;
+	return node_to_ns(node);
+}
 
-	VFS_WARN_ON_ONCE(node_to_ns(node)->ns_type != ns_type);
+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");
 
-	return node_to_ns(node);
+	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
+ * __ns_tree_adjoined_rcu - find the next/previous namespace in the same
  * tree
  * @ns: namespace to start from
+ * @ns_tree: namespace tree to search in
  * @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 ns_tree_root *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));
+		list = rcu_dereference(list_bidir_prev_rcu(&ns->ns_tree_node.ns_list_entry));
 	else
-		list = rcu_dereference(list_next_rcu(&ns->ns_list_node));
-	if (list_is_head(list, &ns_tree->ns_list))
+		list = rcu_dereference(list_next_rcu(&ns->ns_tree_node.ns_list_entry));
+	if (list_is_head(list, &ns_tree->ns_list_head))
 		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);
+	return list_entry_rcu(list, struct ns_common, ns_tree_node.ns_list_entry);
 }
 
 /**
- * ns_tree_gen_id - generate a new namespace id
+ * __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 __ns_tree_gen_id(struct ns_common *ns, u64 id)
 {
-	guard(preempt)();
-	ns->ns_id = gen_cookie_next(&namespace_cookie);
+	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;
 }
+
+struct klistns {
+	u64 __user *uns_ids;
+	u32 nr_ns_ids;
+	u64 last_ns_id;
+	u64 user_ns_id;
+	u32 ns_type;
+	struct user_namespace *user_ns;
+	bool userns_capable;
+	struct ns_common *first_ns;
+};
+
+static void __free_klistns_free(const struct klistns *kls)
+{
+	if (kls->user_ns_id != LISTNS_CURRENT_USER)
+		put_user_ns(kls->user_ns);
+	if (kls->first_ns && kls->first_ns->ops)
+		kls->first_ns->ops->put(kls->first_ns);
+}
+
+#define NS_ALL (PID_NS | USER_NS | MNT_NS | UTS_NS | IPC_NS | NET_NS | CGROUP_NS | TIME_NS)
+
+static int copy_ns_id_req(const struct ns_id_req __user *req,
+			  struct ns_id_req *kreq)
+{
+	int ret;
+	size_t usize;
+
+	BUILD_BUG_ON(sizeof(struct ns_id_req) != NS_ID_REQ_SIZE_VER0);
+
+	ret = get_user(usize, &req->size);
+	if (ret)
+		return -EFAULT;
+	if (unlikely(usize > PAGE_SIZE))
+		return -E2BIG;
+	if (unlikely(usize < NS_ID_REQ_SIZE_VER0))
+		return -EINVAL;
+	memset(kreq, 0, sizeof(*kreq));
+	ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
+	if (ret)
+		return ret;
+	if (kreq->spare != 0)
+		return -EINVAL;
+	if (kreq->ns_type & ~NS_ALL)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static inline int prepare_klistns(struct klistns *kls, struct ns_id_req *kreq,
+				  u64 __user *ns_ids, size_t nr_ns_ids)
+{
+	kls->last_ns_id = kreq->ns_id;
+	kls->user_ns_id = kreq->user_ns_id;
+	kls->nr_ns_ids	= nr_ns_ids;
+	kls->ns_type	= kreq->ns_type;
+	kls->uns_ids	= ns_ids;
+	return 0;
+}
+
+/*
+ * Lookup a namespace owned by owner with id >= ns_id.
+ * Returns the namespace with the smallest id that is >= ns_id.
+ */
+static struct ns_common *lookup_ns_owner_at(u64 ns_id, struct ns_common *owner)
+{
+	struct ns_common *ret = NULL;
+	struct rb_node *node;
+
+	VFS_WARN_ON_ONCE(owner->ns_type != CLONE_NEWUSER);
+
+	guard(ns_tree_locked_reader)();
+
+	node = owner->ns_owner_root.ns_rb.rb_node;
+	while (node) {
+		struct ns_common *ns;
+
+		ns = node_to_ns_owner(node);
+		if (ns_id <= ns->ns_id) {
+			ret = ns;
+			if (ns_id == ns->ns_id)
+				break;
+			node = node->rb_left;
+		} else {
+			node = node->rb_right;
+		}
+	}
+
+	if (ret)
+		ret = ns_get_unless_inactive(ret);
+	return ret;
+}
+
+static struct ns_common *lookup_ns_id(u64 mnt_ns_id, int ns_type)
+{
+	struct ns_common *ns;
+
+	guard(rcu)();
+	ns = ns_tree_lookup_rcu(mnt_ns_id, ns_type);
+	if (!ns)
+		return NULL;
+
+	if (!ns_get_unless_inactive(ns))
+		return NULL;
+
+	return ns;
+}
+
+static inline bool __must_check ns_requested(const struct klistns *kls,
+					     const struct ns_common *ns)
+{
+	return !kls->ns_type || (kls->ns_type & ns->ns_type);
+}
+
+static inline bool __must_check may_list_ns(const struct klistns *kls,
+					    struct ns_common *ns)
+{
+	if (kls->user_ns) {
+		if (kls->userns_capable)
+			return true;
+	} else {
+		struct ns_common *owner;
+		struct user_namespace *user_ns;
+
+		owner = ns_owner(ns);
+		if (owner)
+			user_ns = to_user_ns(owner);
+		else
+			user_ns = &init_user_ns;
+		if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN))
+			return true;
+	}
+
+	if (is_current_namespace(ns))
+		return true;
+
+	if (ns->ns_type != CLONE_NEWUSER)
+		return false;
+
+	if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN))
+		return true;
+
+	return false;
+}
+
+static inline void ns_put(struct ns_common *ns)
+{
+	if (ns && ns->ops)
+		ns->ops->put(ns);
+}
+
+DEFINE_FREE(ns_put, struct ns_common *, if (!IS_ERR_OR_NULL(_T)) ns_put(_T))
+
+static inline struct ns_common *__must_check legitimize_ns(const struct klistns *kls,
+							   struct ns_common *candidate)
+{
+	struct ns_common *ns __free(ns_put) = NULL;
+
+	if (!ns_requested(kls, candidate))
+		return NULL;
+
+	ns = ns_get_unless_inactive(candidate);
+	if (!ns)
+		return NULL;
+
+	if (!may_list_ns(kls, ns))
+		return NULL;
+
+	return no_free_ptr(ns);
+}
+
+static ssize_t do_listns_userns(struct klistns *kls)
+{
+	u64 __user *ns_ids = kls->uns_ids;
+	size_t nr_ns_ids = kls->nr_ns_ids;
+	struct ns_common *ns = NULL, *first_ns = NULL, *prev = NULL;
+	const struct list_head *head;
+	ssize_t ret;
+
+	VFS_WARN_ON_ONCE(!kls->user_ns_id);
+
+	if (kls->user_ns_id == LISTNS_CURRENT_USER)
+		ns = to_ns_common(current_user_ns());
+	else if (kls->user_ns_id)
+		ns = lookup_ns_id(kls->user_ns_id, CLONE_NEWUSER);
+	if (!ns)
+		return -EINVAL;
+	kls->user_ns = to_user_ns(ns);
+
+	/*
+	 * Use the rbtree to find the first namespace we care about and
+	 * then use it's list entry to iterate from there.
+	 */
+	if (kls->last_ns_id) {
+		kls->first_ns = lookup_ns_owner_at(kls->last_ns_id + 1, ns);
+		if (!kls->first_ns)
+			return -ENOENT;
+		first_ns = kls->first_ns;
+	}
+
+	ret = 0;
+	head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head;
+	kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN);
+
+	rcu_read_lock();
+
+	if (!first_ns)
+		first_ns = list_entry_rcu(head->next, typeof(*first_ns), ns_owner_node.ns_list_entry);
+
+	ns = first_ns;
+	list_for_each_entry_from_rcu(ns, head, ns_owner_node.ns_list_entry) {
+		struct ns_common *valid;
+
+		if (!nr_ns_ids)
+			break;
+
+		valid = legitimize_ns(kls, ns);
+		if (!valid)
+			continue;
+
+		rcu_read_unlock();
+
+		ns_put(prev);
+		prev = valid;
+
+		if (put_user(valid->ns_id, ns_ids + ret)) {
+			ns_put(prev);
+			return -EFAULT;
+		}
+
+		nr_ns_ids--;
+		ret++;
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+	ns_put(prev);
+	return ret;
+}
+
+/*
+ * Lookup a namespace with id >= ns_id in either the unified tree or a type-specific tree.
+ * Returns the namespace with the smallest id that is >= ns_id.
+ */
+static struct ns_common *lookup_ns_id_at(u64 ns_id, int ns_type)
+{
+	struct ns_common *ret = NULL;
+	struct ns_tree_root *ns_tree = NULL;
+	struct rb_node *node;
+
+	if (ns_type) {
+		ns_tree = ns_tree_from_type(ns_type);
+		if (!ns_tree)
+			return NULL;
+	}
+
+	guard(ns_tree_locked_reader)();
+
+	if (ns_tree)
+		node = ns_tree->ns_rb.rb_node;
+	else
+		node = ns_unified_root.ns_rb.rb_node;
+
+	while (node) {
+		struct ns_common *ns;
+
+		if (ns_type)
+			ns = node_to_ns(node);
+		else
+			ns = node_to_ns_unified(node);
+
+		if (ns_id <= ns->ns_id) {
+			if (ns_type)
+				ret = node_to_ns(node);
+			else
+				ret = node_to_ns_unified(node);
+			if (ns_id == ns->ns_id)
+				break;
+			node = node->rb_left;
+		} else {
+			node = node->rb_right;
+		}
+	}
+
+	if (ret)
+		ret = ns_get_unless_inactive(ret);
+	return ret;
+}
+
+static inline struct ns_common *first_ns_common(const struct list_head *head,
+						struct ns_tree_root *ns_tree)
+{
+	if (ns_tree)
+		return list_entry_rcu(head->next, struct ns_common, ns_tree_node.ns_list_entry);
+	return list_entry_rcu(head->next, struct ns_common, ns_unified_node.ns_list_entry);
+}
+
+static inline struct ns_common *next_ns_common(struct ns_common *ns,
+					       struct ns_tree_root *ns_tree)
+{
+	if (ns_tree)
+		return list_entry_rcu(ns->ns_tree_node.ns_list_entry.next, struct ns_common, ns_tree_node.ns_list_entry);
+	return list_entry_rcu(ns->ns_unified_node.ns_list_entry.next, struct ns_common, ns_unified_node.ns_list_entry);
+}
+
+static inline bool ns_common_is_head(struct ns_common *ns,
+				     const struct list_head *head,
+				     struct ns_tree_root *ns_tree)
+{
+	if (ns_tree)
+		return &ns->ns_tree_node.ns_list_entry == head;
+	return &ns->ns_unified_node.ns_list_entry == head;
+}
+
+static ssize_t do_listns(struct klistns *kls)
+{
+	u64 __user *ns_ids = kls->uns_ids;
+	size_t nr_ns_ids = kls->nr_ns_ids;
+	struct ns_common *ns, *first_ns = NULL, *prev = NULL;
+	struct ns_tree_root *ns_tree = NULL;
+	const struct list_head *head;
+	u32 ns_type;
+	ssize_t ret;
+
+	if (hweight32(kls->ns_type) == 1)
+		ns_type = kls->ns_type;
+	else
+		ns_type = 0;
+
+	if (ns_type) {
+		ns_tree = ns_tree_from_type(ns_type);
+		if (!ns_tree)
+			return -EINVAL;
+	}
+
+	if (kls->last_ns_id) {
+		kls->first_ns = lookup_ns_id_at(kls->last_ns_id + 1, ns_type);
+		if (!kls->first_ns)
+			return -ENOENT;
+		first_ns = kls->first_ns;
+	}
+
+	ret = 0;
+	if (ns_tree)
+		head = &ns_tree->ns_list_head;
+	else
+		head = &ns_unified_root.ns_list_head;
+
+	rcu_read_lock();
+
+	if (!first_ns)
+		first_ns = first_ns_common(head, ns_tree);
+
+	for (ns = first_ns; !ns_common_is_head(ns, head, ns_tree) && nr_ns_ids;
+	     ns = next_ns_common(ns, ns_tree)) {
+		struct ns_common *valid;
+
+		valid = legitimize_ns(kls, ns);
+		if (!valid)
+			continue;
+
+		rcu_read_unlock();
+
+		ns_put(prev);
+		prev = valid;
+
+		if (put_user(valid->ns_id, ns_ids + ret)) {
+			ns_put(prev);
+			return -EFAULT;
+		}
+
+		nr_ns_ids--;
+		ret++;
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+	ns_put(prev);
+	return ret;
+}
+
+SYSCALL_DEFINE4(listns, const struct ns_id_req __user *, req,
+		u64 __user *, ns_ids, size_t, nr_ns_ids, unsigned int, flags)
+{
+	struct klistns klns __free(klistns_free) = {};
+	const size_t maxcount = 1000000;
+	struct ns_id_req kreq;
+	ssize_t ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (unlikely(nr_ns_ids > maxcount))
+		return -EOVERFLOW;
+
+	if (!access_ok(ns_ids, nr_ns_ids * sizeof(*ns_ids)))
+		return -EFAULT;
+
+	ret = copy_ns_id_req(req, &kreq);
+	if (ret)
+		return ret;
+
+	ret = prepare_klistns(&klns, &kreq, ns_ids, nr_ns_ids);
+	if (ret)
+		return ret;
+
+	if (kreq.user_ns_id)
+		return do_listns_userns(&klns);
+
+	return do_listns(&klns);
+}
diff --git a/kernel/pid.c b/kernel/pid.c
index 4fffec767a63..a31771bc89c1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -71,21 +71,16 @@ static int pid_max_max = PID_MAX_LIMIT;
  * the scheme scales to up to 4 million PIDs, runtime.
  */
 struct pid_namespace init_pid_ns = {
-	.ns.__ns_ref = REFCOUNT_INIT(2),
+	.ns = NS_COMMON_INIT(init_pid_ns),
 	.idr = IDR_INIT(init_pid_ns.idr),
 	.pid_allocated = PIDNS_ADDING,
 	.level = 0,
 	.child_reaper = &init_task,
 	.user_ns = &init_user_ns,
-	.ns.inum = ns_init_inum(&init_pid_ns),
-#ifdef CONFIG_PID_NS
-	.ns.ops = &pidns_operations,
-#endif
 	.pid_max = PID_MAX_DEFAULT,
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
 	.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
 #endif
-	.ns.ns_type = ns_common_type(&init_pid_ns),
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
@@ -117,9 +112,13 @@ static void delayed_put_pid(struct rcu_head *rhp)
 void free_pid(struct pid *pid)
 {
 	int i;
+	struct pid_namespace *active_ns;
 
 	lockdep_assert_not_held(&tasklist_lock);
 
+	active_ns = pid->numbers[pid->level].ns;
+	ns_ref_active_put(active_ns);
+
 	spin_lock(&pidmap_lock);
 	for (i = 0; i <= pid->level; i++) {
 		struct upid *upid = pid->numbers + i;
@@ -283,6 +282,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	}
 	spin_unlock(&pidmap_lock);
 	idr_preload_end();
+	ns_ref_active_get(ns);
 
 	return pid;
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 650be58d8d18..e48f5de41361 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,7 +184,7 @@ struct pid_namespace *copy_pid_ns(u64 flags,
 
 void put_pid_ns(struct pid_namespace *ns)
 {
-	if (ns && ns != &init_pid_ns && ns_ref_put(ns))
+	if (ns && ns_ref_put(ns))
 		schedule_work(&ns->work);
 }
 EXPORT_SYMBOL_GPL(put_pid_ns);
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 5b6997f4dc3d..e76be24b132c 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -478,11 +478,8 @@ const struct proc_ns_operations timens_for_children_operations = {
 };
 
 struct time_namespace init_time_ns = {
-	.ns.ns_type	= ns_common_type(&init_time_ns),
-	.ns.__ns_ref	= REFCOUNT_INIT(3),
+	.ns		= NS_COMMON_INIT(init_time_ns),
 	.user_ns	= &init_user_ns,
-	.ns.inum	= ns_init_inum(&init_time_ns),
-	.ns.ops		= &timens_operations,
 	.frozen_offsets	= true,
 };
 
diff --git a/kernel/user.c b/kernel/user.c
index 0163665914c9..7aef4e679a6a 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -35,6 +35,7 @@ EXPORT_SYMBOL_GPL(init_binfmt_misc);
  * and 1 for... ?
  */
 struct user_namespace init_user_ns = {
+	.ns = NS_COMMON_INIT(init_user_ns),
 	.uid_map = {
 		{
 			.extent[0] = {
@@ -65,14 +66,8 @@ struct user_namespace init_user_ns = {
 			.nr_extents = 1,
 		},
 	},
-	.ns.ns_type = ns_common_type(&init_user_ns),
-	.ns.__ns_ref = REFCOUNT_INIT(3),
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
-	.ns.inum = ns_init_inum(&init_user_ns),
-#ifdef CONFIG_USER_NS
-	.ns.ops = &userns_operations,
-#endif
 	.flags = USERNS_INIT_FLAGS,
 #ifdef CONFIG_KEYS
 	.keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list),