From 3760342fd6312416491d536144e39297fa5b1950 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 29 Oct 2025 13:20:28 +0100 Subject: nstree: assign fixed ids to the initial namespaces The initial set of namespace comes with fixed inode numbers making it easy for userspace to identify them solely based on that information. This has long preceeded anything here. Similarly, let's assign fixed namespace ids for the initial namespaces. Kill the cookie and use a sequentially increasing number. This has the nice side-effect that the owning user namespace will always have a namespace id that is smaller than any of it's descendant namespaces. Link: https://patch.msgid.link/20251029-work-namespace-nstree-listns-v4-15-2e6f823ebdc0@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index e098759ec917..f8bc2aad74d6 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -67,4 +67,18 @@ 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 +}; + #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From 76b6f5dfb3fda76fce1f9990d6fa58adc711122b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 29 Oct 2025 13:20:32 +0100 Subject: nstree: add listns() 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, enhancing existing namespace apis. Currently, there is no direct way for userspace to enumerate namespaces in the system. Applications must resort to scanning /proc//ns/ across all processes, which is: 1. Inefficient - requires iterating over all processes 2. Incomplete - misses inactive namespaces that aren't attached to any running process but are kept alive by file descriptors, bind mounts, or parent namespace references 3. Permission-heavy - requires access to /proc for many processes 4. No ordering or ownership. 5. No filtering per namespace type: Must always iterate and check all namespaces. The list goes on. The listns() system call solves these problems by providing direct kernel-level enumeration of namespaces. It is similar to listmount() but obviously tailored to namespaces. /* * @req: Pointer to struct ns_id_req specifying search parameters * @ns_ids: User buffer to receive namespace IDs * @nr_ns_ids: Size of ns_ids buffer (maximum number of IDs to return) * @flags: Reserved for future use (must be 0) */ ssize_t listns(const struct ns_id_req *req, u64 *ns_ids, size_t nr_ns_ids, unsigned int flags); Returns: - On success: Number of namespace IDs written to ns_ids - On error: Negative error code /* * @size: Structure size * @ns_id: Starting point for iteration; use 0 for first call, then * use the last returned ID for subsequent calls to paginate * @ns_type: Bitmask of namespace types to include (from enum ns_type): * 0: Return all namespace types * MNT_NS: Mount namespaces * NET_NS: Network namespaces * USER_NS: User namespaces * etc. Can be OR'd together * @user_ns_id: Filter results to namespaces owned by this user namespace: * 0: Return all namespaces (subject to permission checks) * LISTNS_CURRENT_USER: Namespaces owned by caller's user namespace * Other value: Namespaces owned by the specified user namespace ID */ struct ns_id_req { __u32 size; /* sizeof(struct ns_id_req) */ __u32 spare; /* Reserved, must be 0 */ __u64 ns_id; /* Last seen namespace ID (for pagination) */ __u32 ns_type; /* Filter by namespace type(s) */ __u32 spare2; /* Reserved, must be 0 */ __u64 user_ns_id; /* Filter by owning user namespace */ }; Example 1: List all namespaces void list_all_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, /* Start from beginning */ .ns_type = 0, /* All types */ .user_ns_id = 0, /* All user namespaces */ }; uint64_t ids[100]; ssize_t ret; printf("All namespaces in the system:\n"); do { ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); break; } for (ssize_t i = 0; i < ret; i++) printf(" Namespace ID: %llu\n", (unsigned long long)ids[i]); /* Continue from last seen ID */ if (ret > 0) req.ns_id = ids[ret - 1]; } while (ret == 100); /* Buffer was full, more may exist */ } Example 2: List network namespaces only void list_network_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = NET_NS, /* Only network namespaces */ .user_ns_id = 0, }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); return; } printf("Network namespaces: %zd found\n", ret); for (ssize_t i = 0; i < ret; i++) printf(" netns ID: %llu\n", (unsigned long long)ids[i]); } Example 3: List namespaces owned by current user namespace void list_owned_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = 0, /* All types */ .user_ns_id = LISTNS_CURRENT_USER, /* Current userns */ }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); return; } printf("Namespaces owned by my user namespace: %zd\n", ret); for (ssize_t i = 0; i < ret; i++) printf(" ns ID: %llu\n", (unsigned long long)ids[i]); } Example 4: List multiple namespace types void list_network_and_mount_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = NET_NS | MNT_NS, /* Network and mount */ .user_ns_id = 0, }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); printf("Network and mount namespaces: %zd found\n", ret); } Example 5: Pagination through large namespace sets void list_all_with_pagination(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = 0, .user_ns_id = 0, }; uint64_t ids[50]; size_t total = 0; ssize_t ret; printf("Enumerating all namespaces with pagination:\n"); while (1) { ret = listns(&req, ids, 50, 0); if (ret < 0) { perror("listns"); break; } if (ret == 0) break; /* No more namespaces */ total += ret; printf(" Batch: %zd namespaces\n", ret); /* Last ID in this batch becomes start of next batch */ req.ns_id = ids[ret - 1]; if (ret < 50) break; /* Partial batch = end of results */ } printf("Total: %zu namespaces\n", total); } Permission Model listns() respects namespace isolation and capabilities: (1) Global listing (user_ns_id = 0): - Requires CAP_SYS_ADMIN in the namespace's owning user namespace - OR the namespace must be in the caller's namespace context (e.g., a namespace the caller is currently using) - User namespaces additionally allow listing if the caller has CAP_SYS_ADMIN in that user namespace itself (2) Owner-filtered listing (user_ns_id != 0): - Requires CAP_SYS_ADMIN in the specified owner user namespace - OR the namespace must be in the caller's namespace context - This allows unprivileged processes to enumerate namespaces they own (3) Visibility: - Only "active" namespaces are listed - A namespace is active if it has a non-zero __ns_ref_active count - This includes namespaces used by running processes, held by open file descriptors, or kept active by bind mounts - Inactive namespaces (kept alive only by internal kernel references) are not visible via listns() Link: https://patch.msgid.link/20251029-work-namespace-nstree-listns-v4-19-2e6f823ebdc0@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index f8bc2aad74d6..a25e38d1c874 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -81,4 +81,48 @@ enum init_ns_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 */ -- cgit v1.2.3