Merge tag 'vfs-6.16-rc1.selftests' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs selftests updates from Christian Brauner:
 "This contains various cleanups, fixes, and extensions for out
  filesystem selftests"

* tag 'vfs-6.16-rc1.selftests' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  selftests/fs/mount-notify: add a test variant running inside userns
  selftests/filesystems: create setup_userns() helper
  selftests/filesystems: create get_unique_mnt_id() helper
  selftests/fs/mount-notify: build with tools include dir
  selftests/mount_settattr: remove duplicate syscall definitions
  selftests/pidfd: move syscall definitions into wrappers.h
  selftests/fs/statmount: build with tools include dir
  selftests/filesystems: move wrapper.h out of overlayfs subdir
  selftests/mount_settattr: ensure that ext4 filesystem can be created
  selftests/mount_settattr: add missing STATX_MNT_ID_UNIQUE define
  selftests/mount_settattr: don't define sys_open_tree() twice

3 files changed, 554 insertions, 0 deletions

diff --git a/tools/include/uapi/linux/fanotify.h b/tools/include/uapi/linux/fanotify.h
new file mode 100644
index 000000000000..e710967c7c26
--- /dev/null
+++ b/tools/include/uapi/linux/fanotify.h
@@ -0,0 +1,274 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FANOTIFY_H
+#define _UAPI_LINUX_FANOTIFY_H
+
+#include <linux/types.h>
+
+/* the following events that user-space can register for */
+#define FAN_ACCESS		0x00000001	/* File was accessed */
+#define FAN_MODIFY		0x00000002	/* File was modified */
+#define FAN_ATTRIB		0x00000004	/* Metadata changed */
+#define FAN_CLOSE_WRITE		0x00000008	/* Writable file closed */
+#define FAN_CLOSE_NOWRITE	0x00000010	/* Unwritable file closed */
+#define FAN_OPEN		0x00000020	/* File was opened */
+#define FAN_MOVED_FROM		0x00000040	/* File was moved from X */
+#define FAN_MOVED_TO		0x00000080	/* File was moved to Y */
+#define FAN_CREATE		0x00000100	/* Subfile was created */
+#define FAN_DELETE		0x00000200	/* Subfile was deleted */
+#define FAN_DELETE_SELF		0x00000400	/* Self was deleted */
+#define FAN_MOVE_SELF		0x00000800	/* Self was moved */
+#define FAN_OPEN_EXEC		0x00001000	/* File was opened for exec */
+
+#define FAN_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define FAN_FS_ERROR		0x00008000	/* Filesystem error */
+
+#define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
+#define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
+#define FAN_OPEN_EXEC_PERM	0x00040000	/* File open/exec in perm check */
+/* #define FAN_DIR_MODIFY	0x00080000 */	/* Deprecated (reserved) */
+
+#define FAN_PRE_ACCESS		0x00100000	/* Pre-content access hook */
+#define FAN_MNT_ATTACH		0x01000000	/* Mount was attached */
+#define FAN_MNT_DETACH		0x02000000	/* Mount was detached */
+
+#define FAN_EVENT_ON_CHILD	0x08000000	/* Interested in child events */
+
+#define FAN_RENAME		0x10000000	/* File was renamed */
+
+#define FAN_ONDIR		0x40000000	/* Event occurred against dir */
+
+/* helper events */
+#define FAN_CLOSE		(FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */
+#define FAN_MOVE		(FAN_MOVED_FROM | FAN_MOVED_TO) /* moves */
+
+/* flags used for fanotify_init() */
+#define FAN_CLOEXEC		0x00000001
+#define FAN_NONBLOCK		0x00000002
+
+/* These are NOT bitwise flags.  Both bits are used together.  */
+#define FAN_CLASS_NOTIF		0x00000000
+#define FAN_CLASS_CONTENT	0x00000004
+#define FAN_CLASS_PRE_CONTENT	0x00000008
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
+				 FAN_CLASS_PRE_CONTENT)
+
+#define FAN_UNLIMITED_QUEUE	0x00000010
+#define FAN_UNLIMITED_MARKS	0x00000020
+#define FAN_ENABLE_AUDIT	0x00000040
+
+/* Flags to determine fanotify event format */
+#define FAN_REPORT_PIDFD	0x00000080	/* Report pidfd for event->pid */
+#define FAN_REPORT_TID		0x00000100	/* event->pid is thread id */
+#define FAN_REPORT_FID		0x00000200	/* Report unique file id */
+#define FAN_REPORT_DIR_FID	0x00000400	/* Report unique directory id */
+#define FAN_REPORT_NAME		0x00000800	/* Report events with name */
+#define FAN_REPORT_TARGET_FID	0x00001000	/* Report dirent target id  */
+#define FAN_REPORT_FD_ERROR	0x00002000	/* event->fd can report error */
+#define FAN_REPORT_MNT		0x00004000	/* Report mount events */
+
+/* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */
+#define FAN_REPORT_DFID_NAME	(FAN_REPORT_DIR_FID | FAN_REPORT_NAME)
+/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */
+#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \
+				     FAN_REPORT_FID | FAN_REPORT_TARGET_FID)
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
+				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
+				 FAN_UNLIMITED_MARKS)
+
+/* flags used for fanotify_modify_mark() */
+#define FAN_MARK_ADD		0x00000001
+#define FAN_MARK_REMOVE		0x00000002
+#define FAN_MARK_DONT_FOLLOW	0x00000004
+#define FAN_MARK_ONLYDIR	0x00000008
+/* FAN_MARK_MOUNT is		0x00000010 */
+#define FAN_MARK_IGNORED_MASK	0x00000020
+#define FAN_MARK_IGNORED_SURV_MODIFY	0x00000040
+#define FAN_MARK_FLUSH		0x00000080
+/* FAN_MARK_FILESYSTEM is	0x00000100 */
+#define FAN_MARK_EVICTABLE	0x00000200
+/* This bit is mutually exclusive with FAN_MARK_IGNORED_MASK bit */
+#define FAN_MARK_IGNORE		0x00000400
+
+/* These are NOT bitwise flags.  Both bits can be used togther.  */
+#define FAN_MARK_INODE		0x00000000
+#define FAN_MARK_MOUNT		0x00000010
+#define FAN_MARK_FILESYSTEM	0x00000100
+#define FAN_MARK_MNTNS		0x00000110
+
+/*
+ * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY
+ * for non-inode mark types.
+ */
+#define FAN_MARK_IGNORE_SURV	(FAN_MARK_IGNORE | FAN_MARK_IGNORED_SURV_MODIFY)
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_MARK_FLAGS	(FAN_MARK_ADD |\
+				 FAN_MARK_REMOVE |\
+				 FAN_MARK_DONT_FOLLOW |\
+				 FAN_MARK_ONLYDIR |\
+				 FAN_MARK_MOUNT |\
+				 FAN_MARK_IGNORED_MASK |\
+				 FAN_MARK_IGNORED_SURV_MODIFY |\
+				 FAN_MARK_FLUSH)
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_EVENTS (FAN_ACCESS |\
+			FAN_MODIFY |\
+			FAN_CLOSE |\
+			FAN_OPEN)
+
+/*
+ * All events which require a permission response from userspace
+ */
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\
+			     FAN_ACCESS_PERM)
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
+#define FAN_ALL_OUTGOING_EVENTS	(FAN_ALL_EVENTS |\
+				 FAN_ALL_PERM_EVENTS |\
+				 FAN_Q_OVERFLOW)
+
+#define FANOTIFY_METADATA_VERSION	3
+
+struct fanotify_event_metadata {
+	__u32 event_len;
+	__u8 vers;
+	__u8 reserved;
+	__u16 metadata_len;
+	__aligned_u64 mask;
+	__s32 fd;
+	__s32 pid;
+};
+
+#define FAN_EVENT_INFO_TYPE_FID		1
+#define FAN_EVENT_INFO_TYPE_DFID_NAME	2
+#define FAN_EVENT_INFO_TYPE_DFID	3
+#define FAN_EVENT_INFO_TYPE_PIDFD	4
+#define FAN_EVENT_INFO_TYPE_ERROR	5
+#define FAN_EVENT_INFO_TYPE_RANGE	6
+#define FAN_EVENT_INFO_TYPE_MNT		7
+
+/* Special info types for FAN_RENAME */
+#define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME	10
+/* Reserved for FAN_EVENT_INFO_TYPE_OLD_DFID	11 */
+#define FAN_EVENT_INFO_TYPE_NEW_DFID_NAME	12
+/* Reserved for FAN_EVENT_INFO_TYPE_NEW_DFID	13 */
+
+/* Variable length info record following event metadata */
+struct fanotify_event_info_header {
+	__u8 info_type;
+	__u8 pad;
+	__u16 len;
+};
+
+/*
+ * Unique file identifier info record.
+ * This structure is used for records of types FAN_EVENT_INFO_TYPE_FID,
+ * FAN_EVENT_INFO_TYPE_DFID and FAN_EVENT_INFO_TYPE_DFID_NAME.
+ * For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null terminated
+ * name immediately after the file handle.
+ */
+struct fanotify_event_info_fid {
+	struct fanotify_event_info_header hdr;
+	__kernel_fsid_t fsid;
+	/*
+	 * Following is an opaque struct file_handle that can be passed as
+	 * an argument to open_by_handle_at(2).
+	 */
+	unsigned char handle[];
+};
+
+/*
+ * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD.
+ * It holds a pidfd for the pid that was responsible for generating an event.
+ */
+struct fanotify_event_info_pidfd {
+	struct fanotify_event_info_header hdr;
+	__s32 pidfd;
+};
+
+struct fanotify_event_info_error {
+	struct fanotify_event_info_header hdr;
+	__s32 error;
+	__u32 error_count;
+};
+
+struct fanotify_event_info_range {
+	struct fanotify_event_info_header hdr;
+	__u32 pad;
+	__u64 offset;
+	__u64 count;
+};
+
+struct fanotify_event_info_mnt {
+	struct fanotify_event_info_header hdr;
+	__u64 mnt_id;
+};
+
+/*
+ * User space may need to record additional information about its decision.
+ * The extra information type records what kind of information is included.
+ * The default is none. We also define an extra information buffer whose
+ * size is determined by the extra information type.
+ *
+ * If the information type is Audit Rule, then the information following
+ * is the rule number that triggered the user space decision that
+ * requires auditing.
+ */
+
+#define FAN_RESPONSE_INFO_NONE		0
+#define FAN_RESPONSE_INFO_AUDIT_RULE	1
+
+struct fanotify_response {
+	__s32 fd;
+	__u32 response;
+};
+
+struct fanotify_response_info_header {
+	__u8 type;
+	__u8 pad;
+	__u16 len;
+};
+
+struct fanotify_response_info_audit_rule {
+	struct fanotify_response_info_header hdr;
+	__u32 rule_number;
+	__u32 subj_trust;
+	__u32 obj_trust;
+};
+
+/* Legit userspace responses to a _PERM event */
+#define FAN_ALLOW	0x01
+#define FAN_DENY	0x02
+/* errno other than EPERM can specified in upper byte of deny response */
+#define FAN_ERRNO_BITS	8
+#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS)
+#define FAN_ERRNO_MASK	((1 << FAN_ERRNO_BITS) - 1)
+#define FAN_DENY_ERRNO(err) \
+	(FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT))
+
+#define FAN_AUDIT	0x10	/* Bitmask to create audit record for result */
+#define FAN_INFO	0x20	/* Bitmask to indicate additional information */
+
+/* No fd set in event */
+#define FAN_NOFD	-1
+#define FAN_NOPIDFD	FAN_NOFD
+#define FAN_EPIDFD	-2
+
+/* Helper functions to deal with fanotify_event_metadata buffers */
+#define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata))
+
+#define FAN_EVENT_NEXT(meta, len) ((len) -= (meta)->event_len, \
+				   (struct fanotify_event_metadata*)(((char *)(meta)) + \
+				   (meta)->event_len))
+
+#define FAN_EVENT_OK(meta, len)	((long)(len) >= (long)FAN_EVENT_METADATA_LEN && \
+				(long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \
+				(long)(meta)->event_len <= (long)(len))
+
+#endif /* _UAPI_LINUX_FANOTIFY_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
new file mode 100644
index 000000000000..7fa67c2031a5
--- /dev/null
+++ b/tools/include/uapi/linux/mount.h
@@ -0,0 +1,235 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+#include <linux/types.h>
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only.  Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
+
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT_SET_GROUP		0x00000100 /* Set sharing group instead */
+#define MOVE_MOUNT_BENEATH		0x00000200 /* Mount beneath top mount */
+#define MOVE_MOUNT__MASK		0x00000377
+
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC		0x00000001
+
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC		0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW	0x00000002
+#define FSPICK_NO_AUTOMOUNT	0x00000004
+#define FSPICK_EMPTY_PATH	0x00000008
+
+/*
+ * The type of fsconfig() call made.
+ */
+enum fsconfig_command {
+	FSCONFIG_SET_FLAG	= 0,	/* Set parameter, supplying no value */
+	FSCONFIG_SET_STRING	= 1,	/* Set parameter, supplying a string value */
+	FSCONFIG_SET_BINARY	= 2,	/* Set parameter, supplying a binary blob value */
+	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
+	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
+	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
+	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
+	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC		0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+	__u64 attr_set;
+	__u64 attr_clr;
+	__u64 propagation;
+	__u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
+
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 mnt_opts;		/* [str] Options (comma separated, escaped) */
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 mnt_ns_id;	/* ID of the mount namespace */
+	__u32 fs_subtype;	/* [str] Subtype of fs_type (if any) */
+	__u32 sb_source;	/* [str] Source string of the mount */
+	__u32 opt_num;		/* Number of fs options */
+	__u32 opt_array;	/* [str] Array of nul terminated fs options */
+	__u32 opt_sec_num;	/* Number of security options */
+	__u32 opt_sec_array;	/* [str] Array of nul terminated security options */
+	__u64 supported_mask;	/* Mask flags that this kernel supports */
+	__u32 mnt_uidmap_num;	/* Number of uid mappings */
+	__u32 mnt_uidmap;	/* [str] Array of uid mappings (as seen from callers namespace) */
+	__u32 mnt_gidmap_num;	/* Number of gid mappings */
+	__u32 mnt_gidmap;	/* [str] Array of gid mappings (as seen from callers namespace) */
+	__u64 __spare2[43];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+	__u64 mnt_ns_id;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+#define MNT_ID_REQ_SIZE_VER1	32 /* sizeof second published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+#define STATMOUNT_MNT_NS_ID		0x00000040U	/* Want/got mnt_ns_id */
+#define STATMOUNT_MNT_OPTS		0x00000080U	/* Want/got mnt_opts */
+#define STATMOUNT_FS_SUBTYPE		0x00000100U	/* Want/got fs_subtype */
+#define STATMOUNT_SB_SOURCE		0x00000200U	/* Want/got sb_source */
+#define STATMOUNT_OPT_ARRAY		0x00000400U	/* Want/got opt_... */
+#define STATMOUNT_OPT_SEC_ARRAY		0x00000800U	/* Want/got opt_sec... */
+#define STATMOUNT_SUPPORTED_MASK	0x00001000U	/* Want/got supported mask flags */
+#define STATMOUNT_MNT_UIDMAP		0x00002000U	/* Want/got uidmap... */
+#define STATMOUNT_MNT_GIDMAP		0x00004000U	/* Want/got gidmap... */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+#define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/nsfs.h b/tools/include/uapi/linux/nsfs.h
new file mode 100644
index 000000000000..34127653fd00
--- /dev/null
+++ b/tools/include/uapi/linux/nsfs.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_NSFS_H
+#define __LINUX_NSFS_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define NSIO	0xb7
+
+/* Returns a file descriptor that refers to an owning user namespace */
+#define NS_GET_USERNS		_IO(NSIO, 0x1)
+/* Returns a file descriptor that refers to a parent namespace */
+#define NS_GET_PARENT		_IO(NSIO, 0x2)
+/* Returns the type of namespace (CLONE_NEW* value) referred to by
+   file descriptor */
+#define NS_GET_NSTYPE		_IO(NSIO, 0x3)
+/* Get owner UID (in the caller's user namespace) for a user namespace */
+#define NS_GET_OWNER_UID	_IO(NSIO, 0x4)
+/* Get the id for a mount namespace */
+#define NS_GET_MNTNS_ID		_IOR(NSIO, 0x5, __u64)
+/* Translate pid from target pid namespace into the caller's pid namespace. */
+#define NS_GET_PID_FROM_PIDNS	_IOR(NSIO, 0x6, int)
+/* Return thread-group leader id of pid in the callers pid namespace. */
+#define NS_GET_TGID_FROM_PIDNS	_IOR(NSIO, 0x7, int)
+/* Translate pid from caller's pid namespace into a target pid namespace. */
+#define NS_GET_PID_IN_PIDNS	_IOR(NSIO, 0x8, int)
+/* Return thread-group leader id of pid in the target pid namespace. */
+#define NS_GET_TGID_IN_PIDNS	_IOR(NSIO, 0x9, int)
+
+struct mnt_ns_info {
+	__u32 size;
+	__u32 nr_mounts;
+	__u64 mnt_ns_id;
+};
+
+#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */
+
+/* Get information about namespace. */
+#define NS_MNT_GET_INFO		_IOR(NSIO, 10, struct mnt_ns_info)
+/* Get next namespace. */
+#define NS_MNT_GET_NEXT		_IOR(NSIO, 11, struct mnt_ns_info)
+/* Get previous namespace. */
+#define NS_MNT_GET_PREV		_IOR(NSIO, 12, struct mnt_ns_info)
+
+#endif /* __LINUX_NSFS_H */