summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/ns/ns_common_types.h196
-rw-r--r--include/linux/ns/nstree_types.h55
-rw-r--r--include/linux/ns_common.h233
-rw-r--r--include/linux/nsfs.h3
-rw-r--r--include/linux/nsproxy.h9
-rw-r--r--include/linux/nstree.h52
-rw-r--r--include/linux/pid_namespace.h3
-rw-r--r--include/linux/pseudo_fs.h1
-rw-r--r--include/linux/syscalls.h4
-rw-r--r--include/linux/user_namespace.h4
-rw-r--r--include/uapi/asm-generic/unistd.h4
-rw-r--r--include/uapi/linux/nsfs.h58
12 files changed, 479 insertions, 143 deletions
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
new file mode 100644
index 000000000000..b332b019b29c
--- /dev/null
+++ b/include/linux/ns/ns_common_types.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NS_COMMON_TYPES_H
+#define _LINUX_NS_COMMON_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/ns/nstree_types.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+
+struct cgroup_namespace;
+struct dentry;
+struct ipc_namespace;
+struct mnt_namespace;
+struct net;
+struct pid_namespace;
+struct proc_ns_operations;
+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 cgroupns_operations;
+extern const struct proc_ns_operations ipcns_operations;
+extern const struct proc_ns_operations mntns_operations;
+extern const struct proc_ns_operations netns_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 timens_operations;
+extern const struct proc_ns_operations timens_for_children_operations;
+extern const struct proc_ns_operations userns_operations;
+extern const struct proc_ns_operations utsns_operations;
+
+/*
+ * Namespace lifetimes are managed via a two-tier reference counting model:
+ *
+ * (1) __ns_ref (refcount_t): Main reference count tracking memory
+ * lifetime. Controls when the namespace structure itself is freed.
+ * It also pins the namespace on the namespace trees whereas (2)
+ * only regulates their visibility to userspace.
+ *
+ * (2) __ns_ref_active (atomic_t): Reference count tracking active users.
+ * Controls visibility of the namespace in the namespace trees.
+ * Any live task that uses the namespace (via nsproxy or cred) holds
+ * an active reference. Any open file descriptor or bind-mount of
+ * the namespace holds an active reference. Once all tasks have
+ * called exited their namespaces and all file descriptors and
+ * bind-mounts have been released the active reference count drops
+ * to zero and the namespace becomes inactive. IOW, the namespace
+ * cannot be listed or opened via file handles anymore.
+ *
+ * Note that it is valid to transition from active to inactive and
+ * back from inactive to active e.g., when resurrecting an inactive
+ * namespace tree via the SIOCGSKNS ioctl().
+ *
+ * Relationship and lifecycle states:
+ *
+ * - Active (__ns_ref_active > 0):
+ * Namespace is actively used and visible to userspace. The namespace
+ * can be reopened via /proc/<pid>/ns/<ns_type>, via namespace file
+ * handles, or discovered via listns().
+ *
+ * - Inactive (__ns_ref_active == 0, __ns_ref > 0):
+ * No tasks are actively using the namespace and it isn't pinned by
+ * any bind-mounts or open file descriptors anymore. But the namespace
+ * is still kept alive by internal references. For example, the user
+ * namespace could be pinned by an open file through file->f_cred
+ * references when one of the now defunct tasks had opened a file and
+ * handed the file descriptor off to another process via a UNIX
+ * sockets. Such references keep the namespace structure alive through
+ * __ns_ref but will not hold an active reference.
+ *
+ * - Destroyed (__ns_ref == 0):
+ * No references remain. The namespace is removed from the tree and freed.
+ *
+ * State transitions:
+ *
+ * Active -> Inactive:
+ * When the last task using the namespace exits it drops its active
+ * references to all namespaces. However, user and pid namespaces
+ * remain accessible until the task has been reaped.
+ *
+ * Inactive -> Active:
+ * An inactive namespace tree might be resurrected due to e.g., the
+ * SIOCGSKNS ioctl() on a socket.
+ *
+ * Inactive -> Destroyed:
+ * When __ns_ref drops to zero the namespace is removed from the
+ * namespaces trees and the memory is freed (after RCU grace period).
+ *
+ * Initial namespaces:
+ * Boot-time namespaces (init_net, init_pid_ns, etc.) start with
+ * __ns_ref_active = 1 and remain active forever.
+ *
+ * @ns_type: type of namespace (e.g., CLONE_NEWNET)
+ * @stashed: cached dentry to be used by the vfs
+ * @ops: namespace operations
+ * @inum: namespace inode number (quickly recycled for non-initial namespaces)
+ * @__ns_ref: main reference count (do not use directly)
+ * @ns_tree: namespace tree nodes and active reference count
+ */
+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 ns_tree;
+ struct rcu_head ns_rcu;
+ };
+};
+
+#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 ns_init_id(__ns) \
+ _Generic((__ns), \
+ struct cgroup_namespace *: CGROUP_NS_INIT_ID, \
+ struct ipc_namespace *: IPC_NS_INIT_ID, \
+ struct mnt_namespace *: MNT_NS_INIT_ID, \
+ struct net *: NET_NS_INIT_ID, \
+ struct pid_namespace *: PID_NS_INIT_ID, \
+ struct time_namespace *: TIME_NS_INIT_ID, \
+ struct user_namespace *: USER_NS_INIT_ID, \
+ struct uts_namespace *: UTS_NS_INIT_ID)
+
+#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)
+
+#endif /* _LINUX_NS_COMMON_TYPES_H */
diff --git a/include/linux/ns/nstree_types.h b/include/linux/ns/nstree_types.h
new file mode 100644
index 000000000000..2fb28ee31efb
--- /dev/null
+++ b/include/linux/ns/nstree_types.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
+#ifndef _LINUX_NSTREE_TYPES_H
+#define _LINUX_NSTREE_TYPES_H
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+/**
+ * struct ns_tree_root - Root of a namespace tree
+ * @ns_rb: Red-black tree root for efficient lookups
+ * @ns_list_head: List head for sequential iteration
+ *
+ * Each namespace tree maintains both an rbtree (for O(log n) lookups)
+ * and a list (for efficient sequential iteration). The list is kept in
+ * the same sorted order as the rbtree.
+ */
+struct ns_tree_root {
+ struct rb_root ns_rb;
+ struct list_head ns_list_head;
+};
+
+/**
+ * struct ns_tree_node - Node in a namespace tree
+ * @ns_node: Red-black tree node
+ * @ns_list_entry: List entry for sequential iteration
+ *
+ * Represents a namespace's position in a tree. Each namespace has
+ * multiple tree nodes for different trees (unified, per-type, owner).
+ */
+struct ns_tree_node {
+ struct rb_node ns_node;
+ struct list_head ns_list_entry;
+};
+
+/**
+ * struct ns_tree - Namespace tree nodes and active reference count
+ * @ns_id: Unique namespace identifier
+ * @__ns_ref_active: Active reference count (do not use directly)
+ * @ns_unified_node: Node in the global namespace tree
+ * @ns_tree_node: Node in the per-type namespace tree
+ * @ns_owner_node: Node in the owner namespace's tree of owned namespaces
+ * @ns_owner_root: Root of the tree of namespaces owned by this namespace
+ * (only used when this namespace is an owner)
+ */
+struct ns_tree {
+ u64 ns_id;
+ atomic_t __ns_ref_active;
+ struct ns_tree_node ns_unified_node;
+ struct ns_tree_node ns_tree_node;
+ struct ns_tree_node ns_owner_node;
+ struct ns_tree_root ns_owner_root;
+};
+
+#endif /* _LINUX_NSTREE_TYPES_H */
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
diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h
index e5a5fa83d36b..731b67fc2fec 100644
--- a/include/linux/nsfs.h
+++ b/include/linux/nsfs.h
@@ -37,4 +37,7 @@ void nsfs_init(void);
#define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns)
+void nsproxy_ns_active_get(struct nsproxy *ns);
+void nsproxy_ns_active_put(struct nsproxy *ns);
+
#endif /* _LINUX_NSFS_H */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index bd118a187dec..5a67648721c7 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -93,10 +93,13 @@ static inline struct cred *nsset_cred(struct nsset *set)
*/
int copy_namespaces(u64 flags, struct task_struct *tsk);
-void exit_task_namespaces(struct task_struct *tsk);
+void switch_cred_namespaces(const struct cred *old, const struct cred *new);
+void exit_nsproxy_namespaces(struct task_struct *tsk);
+void get_cred_namespaces(struct task_struct *tsk);
+void exit_cred_namespaces(struct task_struct *tsk);
void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
int exec_task_namespaces(void);
-void free_nsproxy(struct nsproxy *ns);
+void deactivate_nsproxy(struct nsproxy *ns);
int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
struct cred *, struct fs_struct *);
int __init nsproxy_cache_init(void);
@@ -104,7 +107,7 @@ int __init nsproxy_cache_init(void);
static inline void put_nsproxy(struct nsproxy *ns)
{
if (refcount_dec_and_test(&ns->count))
- free_nsproxy(ns);
+ deactivate_nsproxy(ns);
}
static inline void get_nsproxy(struct nsproxy *ns)
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 */
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 445517a72ad0..0e7ae12c96d2 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -61,8 +61,7 @@ static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
{
- if (ns != &init_pid_ns)
- ns_ref_inc(ns);
+ ns_ref_inc(ns);
return ns;
}
diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h
index 2503f7625d65..a651e60d9410 100644
--- a/include/linux/pseudo_fs.h
+++ b/include/linux/pseudo_fs.h
@@ -9,6 +9,7 @@ struct pseudo_fs_context {
const struct xattr_handler * const *xattr;
const struct dentry_operations *dops;
unsigned long magic;
+ unsigned int s_d_flags;
};
struct pseudo_fs_context *init_pseudo(struct fs_context *fc,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 66c06fcdfe19..cf84d98964b2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -77,6 +77,7 @@ struct cachestat_range;
struct cachestat;
struct statmount;
struct mnt_id_req;
+struct ns_id_req;
struct xattr_args;
struct file_attr;
@@ -437,6 +438,9 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
u64 __user *mnt_ids, size_t nr_mnt_ids,
unsigned int flags);
+asmlinkage long sys_listns(const struct ns_id_req __user *req,
+ u64 __user *ns_ids, size_t nr_ns_ids,
+ unsigned int flags);
asmlinkage long sys_truncate(const char __user *path, long length);
asmlinkage long sys_ftruncate(unsigned int fd, off_t length);
#if BITS_PER_LONG == 32
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 9a9aebbf96b9..9c3be157397e 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -166,13 +166,13 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns,
ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX;
}
-#ifdef CONFIG_USER_NS
-
static inline struct user_namespace *to_user_ns(struct ns_common *ns)
{
return container_of(ns, struct user_namespace, ns);
}
+#ifdef CONFIG_USER_NS
+
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
{
if (ns)
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 04e0077fb4c9..942370b3f5d2 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
__SYSCALL(__NR_file_getattr, sys_file_getattr)
#define __NR_file_setattr 469
__SYSCALL(__NR_file_setattr, sys_file_setattr)
+#define __NR_listns 470
+__SYSCALL(__NR_listns, sys_listns)
#undef __NR_syscalls
-#define __NR_syscalls 470
+#define __NR_syscalls 471
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index e098759ec917..a25e38d1c874 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -67,4 +67,62 @@ struct nsfs_file_handle {
#define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */
#define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */
+enum init_ns_id {
+ IPC_NS_INIT_ID = 1ULL,
+ UTS_NS_INIT_ID = 2ULL,
+ USER_NS_INIT_ID = 3ULL,
+ PID_NS_INIT_ID = 4ULL,
+ CGROUP_NS_INIT_ID = 5ULL,
+ TIME_NS_INIT_ID = 6ULL,
+ NET_NS_INIT_ID = 7ULL,
+ MNT_NS_INIT_ID = 8ULL,
+#ifdef __KERNEL__
+ NS_LAST_INIT_ID = MNT_NS_INIT_ID,
+#endif
+};
+
+enum ns_type {
+ TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */
+ MNT_NS = (1ULL << 17), /* CLONE_NEWNS */
+ CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */
+ UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */
+ IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */
+ USER_NS = (1ULL << 28), /* CLONE_NEWUSER */
+ PID_NS = (1ULL << 29), /* CLONE_NEWPID */
+ NET_NS = (1ULL << 30), /* CLONE_NEWNET */
+};
+
+/**
+ * struct ns_id_req - namespace ID request structure
+ * @size: size of this structure
+ * @spare: reserved for future use
+ * @filter: filter mask
+ * @ns_id: last namespace id
+ * @user_ns_id: owning user namespace ID
+ *
+ * Structure for passing namespace ID and miscellaneous parameters to
+ * statns(2) and listns(2).
+ *
+ * For statns(2) @param represents the request mask.
+ * For listns(2) @param represents the last listed mount id (or zero).
+ */
+struct ns_id_req {
+ __u32 size;
+ __u32 spare;
+ __u64 ns_id;
+ struct /* listns */ {
+ __u32 ns_type;
+ __u32 spare2;
+ __u64 user_ns_id;
+ };
+};
+
+/*
+ * Special @user_ns_id value that can be passed to listns()
+ */
+#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */
+
+/* List of all ns_id_req versions. */
+#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */
+
#endif /* __LINUX_NSFS_H */