diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/ns_common.h | 191 | ||||
| -rw-r--r-- | include/linux/nsfs.h | 3 | ||||
| -rw-r--r-- | include/linux/nsproxy.h | 5 | ||||
| -rw-r--r-- | include/linux/nstree.h | 16 | ||||
| -rw-r--r-- | include/linux/pseudo_fs.h | 1 | ||||
| -rw-r--r-- | include/linux/syscalls.h | 4 | ||||
| -rw-r--r-- | include/linux/user_namespace.h | 4 |
7 files changed, 212 insertions, 12 deletions
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index f5b68b8abb54..bd4492ef6ffc 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -4,7 +4,9 @@ #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; @@ -37,6 +39,67 @@ 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; +/* + * 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. + */ struct ns_common { u32 ns_type; struct dentry *stashed; @@ -46,15 +109,37 @@ struct ns_common { union { struct { u64 ns_id; - struct rb_node ns_tree_node; - struct list_head ns_list_node; + struct /* global namespace rbtree and list */ { + struct rb_node ns_unified_tree_node; + struct list_head ns_unified_list_node; + }; + struct /* per type rbtree and list */ { + struct rb_node ns_tree_node; + struct list_head ns_list_node; + }; + struct /* namespace ownership rbtree and list */ { + struct rb_root ns_owner_tree; /* rbtree of namespaces owned by this namespace */ + struct list_head ns_owner; /* list of namespaces owned by this namespace */ + struct rb_node ns_owner_tree_node; /* node in the owner namespace's rbtree */ + struct list_head ns_owner_entry; /* node in the owner namespace's ns_owned list */ + }; + atomic_t __ns_ref_active; /* do not use directly */ }; 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_initial_namespace(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)); +} #define to_ns_common(__ns) \ _Generic((__ns), \ @@ -97,6 +182,17 @@ void __ns_common_free(struct ns_common *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), \ @@ -119,6 +215,21 @@ void __ns_common_free(struct ns_common *ns); struct user_namespace *: CLONE_NEWUSER, \ struct uts_namespace *: CLONE_NEWUTS) +#define NS_COMMON_INIT(nsname, refs) \ +{ \ + .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(refs), \ + .__ns_ref_active = ATOMIC_INIT(1), \ + .ns_list_node = LIST_HEAD_INIT(nsname.ns.ns_list_node), \ + .ns_owner_entry = LIST_HEAD_INIT(nsname.ns.ns_owner_entry), \ + .ns_owner = LIST_HEAD_INIT(nsname.ns.ns_owner), \ + .ns_unified_list_node = LIST_HEAD_INIT(nsname.ns.ns_unified_list_node), \ +} + #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ @@ -133,21 +244,91 @@ 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 bool __ns_ref_put(struct ns_common *ns) { - return refcount_dec_and_test(&ns->__ns_ref); + 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 (refcount_inc_not_zero(&ns->__ns_ref)) + return true; + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); + return false; +} + +static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns) +{ + return refcount_read(&ns->__ns_ref); } -#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) +#define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns))) #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)) +#define ns_ref_active_read(__ns) \ + ((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0) + +void __ns_ref_active_get_owner(struct ns_common *ns); + +static __always_inline void __ns_ref_active_get(struct ns_common *ns) +{ + WARN_ON_ONCE(atomic_add_negative(1, &ns->__ns_ref_active)); + VFS_WARN_ON_ONCE(is_initial_namespace(ns) && __ns_ref_active_read(ns) <= 0); +} +#define ns_ref_active_get(__ns) \ + do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0) + +static __always_inline bool __ns_ref_active_get_not_zero(struct ns_common *ns) +{ + if (atomic_inc_not_zero(&ns->__ns_ref_active)) { + VFS_WARN_ON_ONCE(!__ns_ref_read(ns)); + return true; + } + return false; +} + +#define ns_ref_active_get_owner(__ns) \ + do { if (__ns) __ns_ref_active_get_owner(to_ns_common(__ns)); } while (0) + +void __ns_ref_active_put_owner(struct ns_common *ns); + +static __always_inline void __ns_ref_active_put(struct ns_common *ns) +{ + if (atomic_dec_and_test(&ns->__ns_ref_active)) { + VFS_WARN_ON_ONCE(is_initial_namespace(ns)); + VFS_WARN_ON_ONCE(!__ns_ref_read(ns)); + __ns_ref_active_put_owner(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) +{ + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) && !__ns_ref_read(ns)); + if (!__ns_ref_active_read(ns)) + return NULL; + if (!__ns_ref_get(ns)) + return NULL; + return ns; +} + +void __ns_ref_active_resurrect(struct ns_common *ns); + +#define ns_ref_active_resurrect(__ns) \ + do { if (__ns) __ns_ref_active_resurrect(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..ac825eddec59 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -93,7 +93,10 @@ 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); diff --git a/include/linux/nstree.h b/include/linux/nstree.h index 8b8636690473..38674c6fa4f7 100644 --- a/include/linux/nstree.h +++ b/include/linux/nstree.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ #ifndef _LINUX_NSTREE_H #define _LINUX_NSTREE_H @@ -8,6 +9,7 @@ #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; @@ -29,7 +31,11 @@ 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); +#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 *ns_tree); void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree); struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type); @@ -37,9 +43,9 @@ struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns, struct ns_tree *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 *ns_tree, u64 id) { - ns_tree_gen_id(ns); + __ns_tree_gen_id(ns, id); __ns_tree_add_raw(ns, ns_tree); } @@ -59,7 +65,9 @@ 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 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) |