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

tools/include/uapi/linux/fanotify.h

···
+/* 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 */

tools/include/uapi/linux/mount.h

···
+#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 */

tools/include/uapi/linux/nsfs.h

···
+/* 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 */

tools/testing/selftests/filesystems/mount-notify/.gitignore

···
 # SPDX-License-Identifier: GPL-2.0-only
 /*_test
+/*_test_ns

tools/testing/selftests/filesystems/mount-notify/Makefile

···
 # SPDX-License-Identifier: GPL-2.0-or-later
 
-CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
-TEST_GEN_PROGS := mount-notify_test
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+LDLIBS += -lcap
+
+TEST_GEN_PROGS := mount-notify_test mount-notify_test_ns
 
 include ../../lib.mk
+
+$(OUTPUT)/mount-notify_test: ../utils.c
+$(OUTPUT)/mount-notify_test_ns: ../utils.c

tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c

···
 #include <string.h>
 #include <sys/stat.h>
 #include <sys/mount.h>
-#include <linux/fanotify.h>
 #include <unistd.h>
-#include <sys/fanotify.h>
 #include <sys/syscall.h>
 
 #include "../../kselftest_harness.h"
 #include "../statmount/statmount.h"
+#include "../utils.h"
 
-#ifndef FAN_MNT_ATTACH
-struct fanotify_event_info_mnt {
-	struct fanotify_event_info_header hdr;
-	__u64 mnt_id;
-};
-#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */
+// Needed for linux/fanotify.h
+#ifndef __kernel_fsid_t
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
 #endif
 
-#ifndef FAN_MNT_DETACH
-#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */
-#endif
-
-#ifndef FAN_REPORT_MNT
-#define FAN_REPORT_MNT 0x00004000 /* Report mount events */
-#endif
-
-#ifndef FAN_MARK_MNTNS
-#define FAN_MARK_MNTNS 0x00000110
-#endif
-
-static uint64_t get_mnt_id(struct __test_metadata *const _metadata,
-			   const char *path)
-{
-	struct statx sx;
-
-	ASSERT_EQ(statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx), 0);
-	ASSERT_TRUE(!!(sx.stx_mask & STATX_MNT_ID_UNIQUE));
-	return sx.stx_mnt_id;
-}
+#include <sys/fanotify.h>
 
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
···
 
 	ASSERT_EQ(mkdir("b", 0700), 0);
 
-	self->root_id = get_mnt_id(_metadata, "/");
+	self->root_id = get_unique_mnt_id("/");
 	ASSERT_NE(self->root_id, 0);
 
 	for (i = 0; i < NUM_FAN_FDS; i++) {

tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2025 Miklos Szeredi <[e-mail]>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+#include "../../kselftest_harness.h"
+#include "../../pidfd/pidfd.h"
+#include "../statmount/statmount.h"
+#include "../utils.h"
+
+// Needed for linux/fanotify.h
+#ifndef __kernel_fsid_t
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#endif
+
+#include <sys/fanotify.h>
+
+static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
+
+static const int mark_types[] = {
+	FAN_MARK_FILESYSTEM,
+	FAN_MARK_MOUNT,
+	FAN_MARK_INODE
+};
+
+static const int mark_cmds[] = {
+	FAN_MARK_ADD,
+	FAN_MARK_REMOVE,
+	FAN_MARK_FLUSH
+};
+
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
+
+FIXTURE(fanotify) {
+	int fan_fd[NUM_FAN_FDS];
+	char buf[256];
+	unsigned int rem;
+	void *next;
+	char root_mntpoint[sizeof(root_mntpoint_templ)];
+	int orig_root;
+	int orig_ns_fd;
+	int ns_fd;
+	uint64_t root_id;
+};
+
+FIXTURE_SETUP(fanotify)
+{
+	int i, ret;
+
+	self->orig_ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(self->orig_ns_fd, 0);
+
+	ret = setup_userns();
+	ASSERT_EQ(ret, 0);
+
+	self->ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(self->ns_fd, 0);
+
+	strcpy(self->root_mntpoint, root_mntpoint_templ);
+	ASSERT_NE(mkdtemp(self->root_mntpoint), NULL);
+
+	self->orig_root = open("/", O_PATH | O_CLOEXEC);
+	ASSERT_GE(self->orig_root, 0);
+
+	ASSERT_EQ(mount("tmpfs", self->root_mntpoint, "tmpfs", 0, NULL), 0);
+
+	ASSERT_EQ(chroot(self->root_mntpoint), 0);
+
+	ASSERT_EQ(chdir("/"), 0);
+
+	ASSERT_EQ(mkdir("a", 0700), 0);
+
+	ASSERT_EQ(mkdir("b", 0700), 0);
+
+	self->root_id = get_unique_mnt_id("/");
+	ASSERT_NE(self->root_id, 0);
+
+	for (i = 0; i < NUM_FAN_FDS; i++) {
+		int fan_fd = fanotify_init(FAN_REPORT_FID, 0);
+		// Verify that watching tmpfs mounted inside userns is allowed
+		ret = fanotify_mark(fan_fd, FAN_MARK_ADD | mark_types[i],
+				    FAN_OPEN, AT_FDCWD, "/");
+		ASSERT_EQ(ret, 0);
+		// ...but watching entire orig root filesystem is not allowed
+		ret = fanotify_mark(fan_fd, FAN_MARK_ADD | FAN_MARK_FILESYSTEM,
+				    FAN_OPEN, self->orig_root, ".");
+		ASSERT_NE(ret, 0);
+		close(fan_fd);
+
+		self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+						0);
+		ASSERT_GE(self->fan_fd[i], 0);
+		// Verify that watching mntns where group was created is allowed
+		ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+				    FAN_MARK_MNTNS,
+				    FAN_MNT_ATTACH | FAN_MNT_DETACH,
+				    self->ns_fd, NULL);
+		ASSERT_EQ(ret, 0);
+		// ...but watching orig mntns is not allowed
+		ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+				    FAN_MARK_MNTNS,
+				    FAN_MNT_ATTACH | FAN_MNT_DETACH,
+				    self->orig_ns_fd, NULL);
+		ASSERT_NE(ret, 0);
+		// On fd[0] we do an extra ADD that changes nothing.
+		// On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+		ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+				    FAN_MARK_MNTNS,
+				    FAN_MNT_ATTACH | FAN_MNT_DETACH,
+				    self->ns_fd, NULL);
+		ASSERT_EQ(ret, 0);
+	}
+
+	self->rem = 0;
+}
+
+FIXTURE_TEARDOWN(fanotify)
+{
+	int i;
+
+	ASSERT_EQ(self->rem, 0);
+	for (i = 0; i < NUM_FAN_FDS; i++)
+		close(self->fan_fd[i]);
+
+	ASSERT_EQ(fchdir(self->orig_root), 0);
+
+	ASSERT_EQ(chroot("."), 0);
+
+	EXPECT_EQ(umount2(self->root_mntpoint, MNT_DETACH), 0);
+	EXPECT_EQ(chdir(self->root_mntpoint), 0);
+	EXPECT_EQ(chdir("/"), 0);
+	EXPECT_EQ(rmdir(self->root_mntpoint), 0);
+}
+
+static uint64_t expect_notify(struct __test_metadata *const _metadata,
+			      FIXTURE_DATA(fanotify) *self,
+			      uint64_t *mask)
+{
+	struct fanotify_event_metadata *meta;
+	struct fanotify_event_info_mnt *mnt;
+	unsigned int thislen;
+
+	if (!self->rem) {
+		ssize_t len;
+		int i;
+
+		for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+			len = read(self->fan_fd[i], self->buf,
+				   sizeof(self->buf));
+			if (i > 0) {
+				// Groups 1,2 should get EAGAIN
+				ASSERT_EQ(len, -1);
+				ASSERT_EQ(errno, EAGAIN);
+			} else {
+				// Group 0 should get events
+				ASSERT_GT(len, 0);
+			}
+		}
+
+		self->rem = len;
+		self->next = (void *) self->buf;
+	}
+
+	meta = self->next;
+	ASSERT_TRUE(FAN_EVENT_OK(meta, self->rem));
+
+	thislen = meta->event_len;
+	self->rem -= thislen;
+	self->next += thislen;
+
+	*mask = meta->mask;
+	thislen -= sizeof(*meta);
+
+	mnt = ((void *) meta) + meta->event_len - thislen;
+
+	ASSERT_EQ(thislen, sizeof(*mnt));
+
+	return mnt->mnt_id;
+}
+
+static void expect_notify_n(struct __test_metadata *const _metadata,
+				 FIXTURE_DATA(fanotify) *self,
+				 unsigned int n, uint64_t mask[], uint64_t mnts[])
+{
+	unsigned int i;
+
+	for (i = 0; i < n; i++)
+		mnts[i] = expect_notify(_metadata, self, &mask[i]);
+}
+
+static uint64_t expect_notify_mask(struct __test_metadata *const _metadata,
+				   FIXTURE_DATA(fanotify) *self,
+				   uint64_t expect_mask)
+{
+	uint64_t mntid, mask;
+
+	mntid = expect_notify(_metadata, self, &mask);
+	ASSERT_EQ(expect_mask, mask);
+
+	return mntid;
+}
+
+
+static void expect_notify_mask_n(struct __test_metadata *const _metadata,
+				 FIXTURE_DATA(fanotify) *self,
+				 uint64_t mask, unsigned int n, uint64_t mnts[])
+{
+	unsigned int i;
+
+	for (i = 0; i < n; i++)
+		mnts[i] = expect_notify_mask(_metadata, self, mask);
+}
+
+static void verify_mount_ids(struct __test_metadata *const _metadata,
+			     const uint64_t list1[], const uint64_t list2[],
+			     size_t num)
+{
+	unsigned int i, j;
+
+	// Check that neither list has any duplicates
+	for (i = 0; i < num; i++) {
+		for (j = 0; j < num; j++) {
+			if (i != j) {
+				ASSERT_NE(list1[i], list1[j]);
+				ASSERT_NE(list2[i], list2[j]);
+			}
+		}
+	}
+	// Check that all list1 memebers can be found in list2. Together with
+	// the above it means that the list1 and list2 represent the same sets.
+	for (i = 0; i < num; i++) {
+		for (j = 0; j < num; j++) {
+			if (list1[i] == list2[j])
+				break;
+		}
+		ASSERT_NE(j, num);
+	}
+}
+
+static void check_mounted(struct __test_metadata *const _metadata,
+			  const uint64_t mnts[], size_t num)
+{
+	ssize_t ret;
+	uint64_t *list;
+
+	list = malloc((num + 1) * sizeof(list[0]));
+	ASSERT_NE(list, NULL);
+
+	ret = listmount(LSMT_ROOT, 0, 0, list, num + 1, 0);
+	ASSERT_EQ(ret, num);
+
+	verify_mount_ids(_metadata, mnts, list, num);
+
+	free(list);
+}
+
+static void setup_mount_tree(struct __test_metadata *const _metadata,
+			    int log2_num)
+{
+	int ret, i;
+
+	ret = mount("", "/", NULL, MS_SHARED, NULL);
+	ASSERT_EQ(ret, 0);
+
+	for (i = 0; i < log2_num; i++) {
+		ret = mount("/", "/", NULL, MS_BIND, NULL);
+		ASSERT_EQ(ret, 0);
+	}
+}
+
+TEST_F(fanotify, bind)
+{
+	int ret;
+	uint64_t mnts[2] = { self->root_id };
+
+	ret = mount("/", "/", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+	ASSERT_NE(mnts[0], mnts[1]);
+
+	check_mounted(_metadata, mnts, 2);
+
+	// Cleanup
+	uint64_t detach_id;
+	ret = umount("/");
+	ASSERT_EQ(ret, 0);
+
+	detach_id = expect_notify_mask(_metadata, self, FAN_MNT_DETACH);
+	ASSERT_EQ(detach_id, mnts[1]);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, move)
+{
+	int ret;
+	uint64_t mnts[2] = { self->root_id };
+	uint64_t move_id;
+
+	ret = mount("/", "/a", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+	ASSERT_NE(mnts[0], mnts[1]);
+
+	check_mounted(_metadata, mnts, 2);
+
+	ret = move_mount(AT_FDCWD, "/a", AT_FDCWD, "/b", 0);
+	ASSERT_EQ(ret, 0);
+
+	move_id = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH | FAN_MNT_DETACH);
+	ASSERT_EQ(move_id, mnts[1]);
+
+	// Cleanup
+	ret = umount("/b");
+	ASSERT_EQ(ret, 0);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, propagate)
+{
+	const unsigned int log2_num = 4;
+	const unsigned int num = (1 << log2_num);
+	uint64_t mnts[num];
+
+	setup_mount_tree(_metadata, log2_num);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, num - 1, mnts + 1);
+
+	mnts[0] = self->root_id;
+	check_mounted(_metadata, mnts, num);
+
+	// Cleanup
+	int ret;
+	uint64_t mnts2[num];
+	ret = umount2("/", MNT_DETACH);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("", "/", NULL, MS_PRIVATE, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts2[0] = self->root_id;
+	expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, num - 1, mnts2 + 1);
+	verify_mount_ids(_metadata, mnts, mnts2, num);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, fsmount)
+{
+	int ret, fs, mnt;
+	uint64_t mnts[2] = { self->root_id };
+
+	fs = fsopen("tmpfs", 0);
+	ASSERT_GE(fs, 0);
+
+	ret = fsconfig(fs, FSCONFIG_CMD_CREATE, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+
+	mnt = fsmount(fs, 0, 0);
+	ASSERT_GE(mnt, 0);
+
+	close(fs);
+
+	ret = move_mount(mnt, "", AT_FDCWD, "/a", MOVE_MOUNT_F_EMPTY_PATH);
+	ASSERT_EQ(ret, 0);
+
+	close(mnt);
+
+	mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+	ASSERT_NE(mnts[0], mnts[1]);
+
+	check_mounted(_metadata, mnts, 2);
+
+	// Cleanup
+	uint64_t detach_id;
+	ret = umount("/a");
+	ASSERT_EQ(ret, 0);
+
+	detach_id = expect_notify_mask(_metadata, self, FAN_MNT_DETACH);
+	ASSERT_EQ(detach_id, mnts[1]);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, reparent)
+{
+	uint64_t mnts[6] = { self->root_id };
+	uint64_t dmnts[3];
+	uint64_t masks[3];
+	unsigned int i;
+	int ret;
+
+	// Create setup with a[1] -> b[2] propagation
+	ret = mount("/", "/a", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("", "/a", NULL, MS_SHARED, NULL);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("/a", "/b", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("", "/b", NULL, MS_SLAVE, NULL);
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 1);
+
+	check_mounted(_metadata, mnts, 3);
+
+	// Mount on a[3], which is propagated to b[4]
+	ret = mount("/", "/a", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 3);
+
+	check_mounted(_metadata, mnts, 5);
+
+	// Mount on b[5], not propagated
+	ret = mount("/", "/b", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts[5] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+
+	check_mounted(_metadata, mnts, 6);
+
+	// Umount a[3], which is propagated to b[4], but not b[5]
+	// This will result in b[5] "falling" on b[2]
+	ret = umount("/a");
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_n(_metadata, self, 3, masks, dmnts);
+	verify_mount_ids(_metadata, mnts + 3, dmnts, 3);
+
+	for (i = 0; i < 3; i++) {
+		if (dmnts[i] == mnts[5]) {
+			ASSERT_EQ(masks[i], FAN_MNT_ATTACH | FAN_MNT_DETACH);
+		} else {
+			ASSERT_EQ(masks[i], FAN_MNT_DETACH);
+		}
+	}
+
+	mnts[3] = mnts[5];
+	check_mounted(_metadata, mnts, 4);
+
+	// Cleanup
+	ret = umount("/b");
+	ASSERT_EQ(ret, 0);
+
+	ret = umount("/a");
+	ASSERT_EQ(ret, 0);
+
+	ret = umount("/b");
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, 3, dmnts);
+	verify_mount_ids(_metadata, mnts + 1, dmnts, 3);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, rmdir)
+{
+	uint64_t mnts[3] = { self->root_id };
+	int ret;
+
+	ret = mount("/", "/a", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("/", "/a/b", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 1);
+
+	check_mounted(_metadata, mnts, 3);
+
+	ret = chdir("/a");
+	ASSERT_EQ(ret, 0);
+
+	ret = fork();
+	ASSERT_GE(ret, 0);
+
+	if (ret == 0) {
+		chdir("/");
+		unshare(CLONE_NEWNS);
+		mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
+		umount2("/a", MNT_DETACH);
+		// This triggers a detach in the other namespace
+		rmdir("/a");
+		exit(0);
+	}
+	wait(NULL);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, 2, mnts + 1);
+	check_mounted(_metadata, mnts, 1);
+
+	// Cleanup
+	ret = chdir("/");
+	ASSERT_EQ(ret, 0);
+}
+
+TEST_F(fanotify, pivot_root)
+{
+	uint64_t mnts[3] = { self->root_id };
+	uint64_t mnts2[3];
+	int ret;
+
+	ret = mount("tmpfs", "/a", "tmpfs", 0, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts[2] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+
+	ret = mkdir("/a/new", 0700);
+	ASSERT_EQ(ret, 0);
+
+	ret = mkdir("/a/old", 0700);
+	ASSERT_EQ(ret, 0);
+
+	ret = mount("/a", "/a/new", NULL, MS_BIND, NULL);
+	ASSERT_EQ(ret, 0);
+
+	mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+	check_mounted(_metadata, mnts, 3);
+
+	ret = syscall(SYS_pivot_root, "/a/new", "/a/new/old");
+	ASSERT_EQ(ret, 0);
+
+	expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH | FAN_MNT_DETACH, 2, mnts2);
+	verify_mount_ids(_metadata, mnts, mnts2, 2);
+	check_mounted(_metadata, mnts, 3);
+
+	// Cleanup
+	ret = syscall(SYS_pivot_root, "/old", "/old/a/new");
+	ASSERT_EQ(ret, 0);
+
+	ret = umount("/a/new");
+	ASSERT_EQ(ret, 0);
+
+	ret = umount("/a");
+	ASSERT_EQ(ret, 0);
+
+	check_mounted(_metadata, mnts, 1);
+}
+
+TEST_HARNESS_MAIN

tools/testing/selftests/filesystems/overlayfs/Makefile

···
 CFLAGS += $(KHDR_INCLUDES)
 LDLIBS += -lcap
 
-LOCAL_HDRS += wrappers.h log.h
+LOCAL_HDRS += ../wrappers.h log.h
 
 TEST_GEN_PROGS := dev_in_maps
 TEST_GEN_PROGS += set_layers_via_fds

tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c

···
 
 #include "../../kselftest.h"
 #include "log.h"
-#include "wrappers.h"
+#include "../wrappers.h"
 
 static long get_file_dev_and_inode(void *addr, struct statx *stx)
 {

tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c

···
 #include "../../pidfd/pidfd.h"
 #include "log.h"
 #include "../utils.h"
-#include "wrappers.h"
+#include "../wrappers.h"
 
 FIXTURE(set_layers_via_fds) {
 	int pidfd;

tools/testing/selftests/filesystems/overlayfs/wrappers.h tools/testing/selftests/filesystems/wrappers.h

···
 #include <linux/mount.h>
 #include <sys/syscall.h>
 
+#ifndef STATX_MNT_ID_UNIQUE
+#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
+#endif
+
 static inline int sys_fsopen(const char *fsname, unsigned int flags)
 {
 	return syscall(__NR_fsopen, fsname, flags);
···
 #define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
 #endif
 
+#ifndef MOVE_MOUNT_T_EMPTY_PATH
+#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#endif
+
+#ifndef __NR_move_mount
+	#if defined __alpha__
+		#define __NR_move_mount 539
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_move_mount 4429
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_move_mount 6429
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_move_mount 5429
+		#endif
+	#else
+		#define __NR_move_mount 429
+	#endif
+#endif
+
 static inline int sys_move_mount(int from_dfd, const char *from_pathname,
 				 int to_dfd, const char *to_pathname,
 				 unsigned int flags)
···
 #endif
 
 #ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+#endif
+
+#ifndef __NR_open_tree
+	#if defined __alpha__
+		#define __NR_open_tree 538
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_open_tree 4428
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_open_tree 6428
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_open_tree 5428
+		#endif
+	#else
+		#define __NR_open_tree 428
+	#endif
 #endif
 
 static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)

tools/testing/selftests/filesystems/statmount/Makefile

···
 # SPDX-License-Identifier: GPL-2.0-or-later
 
-CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+LDLIBS += -lcap
+
 TEST_GEN_PROGS := statmount_test statmount_test_ns listmount_test
 
 include ../../lib.mk
+
+$(OUTPUT)/statmount_test_ns: ../utils.c

tools/testing/selftests/filesystems/statmount/statmount.h

···
 #include <linux/mount.h>
 #include <asm/unistd.h>
 
+#ifndef __NR_statmount
+	#if defined __alpha__
+		#define __NR_statmount 567
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_statmount 4457
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_statmount 6457
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_statmount 5457
+		#endif
+	#else
+		#define __NR_statmount 457
+	#endif
+#endif
+
+#ifndef __NR_listmount
+	#if defined __alpha__
+		#define __NR_listmount 568
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_listmount 4458
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_listmount 6458
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_listmount 5458
+		#endif
+	#else
+		#define __NR_listmount 458
+	#endif
+#endif
+
 static inline int statmount(uint64_t mnt_id, uint64_t mnt_ns_id, uint64_t mask,
 			    struct statmount *buf, size_t bufsize,
 			    unsigned int flags)

tools/testing/selftests/filesystems/statmount/statmount_test_ns.c

···
 #include <linux/stat.h>
 
 #include "statmount.h"
+#include "../utils.h"
 #include "../../kselftest.h"
 
 #define NSID_PASS 0
···
 	return NSID_PASS;
 }
 
-static int get_mnt_id(const char *path, uint64_t *mnt_id)
-{
-	struct statx sx;
-	int ret;
-
-	ret = statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx);
-	if (ret == -1) {
-		ksft_print_msg("retrieving unique mount ID for %s: %s\n", path,
-			       strerror(errno));
-		return NSID_ERROR;
-	}
-
-	if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) {
-		ksft_print_msg("no unique mount ID available for %s\n", path);
-		return NSID_ERROR;
-	}
-
-	*mnt_id = sx.stx_mnt_id;
-	return NSID_PASS;
-}
-
-static int write_file(const char *path, const char *val)
-{
-	int fd = open(path, O_WRONLY);
-	size_t len = strlen(val);
-	int ret;
-
-	if (fd == -1) {
-		ksft_print_msg("opening %s for write: %s\n", path, strerror(errno));
-		return NSID_ERROR;
-	}
-
-	ret = write(fd, val, len);
-	if (ret == -1) {
-		ksft_print_msg("writing to %s: %s\n", path, strerror(errno));
-		return NSID_ERROR;
-	}
-	if (ret != len) {
-		ksft_print_msg("short write to %s\n", path);
-		return NSID_ERROR;
-	}
-
-	ret = close(fd);
-	if (ret == -1) {
-		ksft_print_msg("closing %s\n", path);
-		return NSID_ERROR;
-	}
-
-	return NSID_PASS;
-}
-
 static int setup_namespace(void)
 {
-	int ret;
-	char buf[32];
-	uid_t uid = getuid();
-	gid_t gid = getgid();
-
-	ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID);
-	if (ret == -1)
-		ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
-				   strerror(errno));
-
-	sprintf(buf, "0 %d 1", uid);
-	ret = write_file("/proc/self/uid_map", buf);
-	if (ret != NSID_PASS)
-		return ret;
-	ret = write_file("/proc/self/setgroups", "deny");
-	if (ret != NSID_PASS)
-		return ret;
-	sprintf(buf, "0 %d 1", gid);
-	ret = write_file("/proc/self/gid_map", buf);
-	if (ret != NSID_PASS)
-		return ret;
-
-	ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
-	if (ret == -1) {
-		ksft_print_msg("making mount tree private: %s\n",
-			       strerror(errno));
+	if (setup_userns() != 0)
 		return NSID_ERROR;
-	}
 
 	return NSID_PASS;
 }
···
 	if (ret != NSID_PASS)
 		return ret;
 
-	ret = get_mnt_id("/", &root_id);
-	if (ret != NSID_PASS)
-		return ret;
+	root_id = get_unique_mnt_id("/");
+	if (!root_id)
+		return NSID_ERROR;
 
 	ret = statmount(root_id, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0);
 	if (ret == -1) {

tools/testing/selftests/filesystems/utils.c

···
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/xattr.h>
+#include <sys/mount.h>
 
+#include "../kselftest.h"
+#include "wrappers.h"
 #include "utils.h"
 
 #define MAX_USERNS_LEVEL 32
···
 	return fret;
 }
 
+static int write_file(const char *path, const char *val)
+{
+	int fd = open(path, O_WRONLY);
+	size_t len = strlen(val);
+	int ret;
+
+	if (fd == -1) {
+		ksft_print_msg("opening %s for write: %s\n", path, strerror(errno));
+		return -1;
+	}
+
+	ret = write(fd, val, len);
+	if (ret == -1) {
+		ksft_print_msg("writing to %s: %s\n", path, strerror(errno));
+		return -1;
+	}
+	if (ret != len) {
+		ksft_print_msg("short write to %s\n", path);
+		return -1;
+	}
+
+	ret = close(fd);
+	if (ret == -1) {
+		ksft_print_msg("closing %s\n", path);
+		return -1;
+	}
+
+	return 0;
+}
+
+int setup_userns(void)
+{
+	int ret;
+	char buf[32];
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+
+	ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID);
+	if (ret) {
+		ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
+				   strerror(errno));
+		return ret;
+	}
+
+	sprintf(buf, "0 %d 1", uid);
+	ret = write_file("/proc/self/uid_map", buf);
+	if (ret)
+		return ret;
+	ret = write_file("/proc/self/setgroups", "deny");
+	if (ret)
+		return ret;
+	sprintf(buf, "0 %d 1", gid);
+	ret = write_file("/proc/self/gid_map", buf);
+	if (ret)
+		return ret;
+
+	ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
+	if (ret) {
+		ksft_print_msg("making mount tree private: %s\n", strerror(errno));
+		return ret;
+	}
+
+	return 0;
+}
+
 /* caps_down - lower all effective caps */
 int caps_down(void)
 {
···
 out:
 	cap_free(caps);
 	return fret;
+}
+
+uint64_t get_unique_mnt_id(const char *path)
+{
+	struct statx sx;
+	int ret;
+
+	ret = statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx);
+	if (ret == -1) {
+		ksft_print_msg("retrieving unique mount ID for %s: %s\n", path,
+			 strerror(errno));
+		return 0;
+	}
+
+	if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) {
+		ksft_print_msg("no unique mount ID available for %s\n", path);
+		return 0;
+	}
+
+	return sx.stx_mnt_id;
 }

tools/testing/selftests/filesystems/utils.h

···
 extern int cap_down(cap_value_t down);
 
 extern bool switch_ids(uid_t uid, gid_t gid);
+extern int setup_userns(void);
 
 static inline bool switch_userns(int fd, uid_t uid, gid_t gid, bool drop_caps)
 {
···
 
 	return true;
 }
+
+extern uint64_t get_unique_mnt_id(const char *path);
 
 #endif /* __IDMAP_UTILS_H */

tools/testing/selftests/mount_setattr/Makefile

···
 # Makefile for mount selftests.
 CFLAGS = -g $(KHDR_INCLUDES) -Wall -O2 -pthread
 
+LOCAL_HDRS += ../filesystems/wrappers.h
+
 TEST_GEN_PROGS := mount_setattr_test
 
 include ../lib.mk

tools/testing/selftests/mount_setattr/mount_setattr_test.c

···
 #include <stdarg.h>
 #include <linux/mount.h>
 
-#include "../filesystems/overlayfs/wrappers.h"
+#include "../filesystems/wrappers.h"
 #include "../kselftest_harness.h"
 
 #ifndef CLONE_NEWNS
···
 	#endif
 #endif
 
-#ifndef __NR_open_tree
-	#if defined __alpha__
-		#define __NR_open_tree 538
-	#elif defined _MIPS_SIM
-		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
-			#define __NR_open_tree 4428
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
-			#define __NR_open_tree 6428
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
-			#define __NR_open_tree 5428
-		#endif
-	#elif defined __ia64__
-		#define __NR_open_tree (428 + 1024)
-	#else
-		#define __NR_open_tree 428
-	#endif
-#endif
-
-#ifndef __NR_move_mount
-	#if defined __alpha__
-		#define __NR_move_mount 539
-	#elif defined _MIPS_SIM
-		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
-			#define __NR_move_mount 4429
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
-			#define __NR_move_mount 6429
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
-			#define __NR_move_mount 5429
-		#endif
-	#elif defined __ia64__
-		#define __NR_move_mount (428 + 1024)
-	#else
-		#define __NR_move_mount 429
-	#endif
-#endif
-
 #ifndef MOUNT_ATTR_IDMAP
 #define MOUNT_ATTR_IDMAP 0x00100000
 #endif
···
 				    struct mount_attr *attr, size_t size)
 {
 	return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
-}
-
-#ifndef OPEN_TREE_CLONE
-#define OPEN_TREE_CLONE 1
-#endif
-
-#ifndef OPEN_TREE_CLOEXEC
-#define OPEN_TREE_CLOEXEC O_CLOEXEC
-#endif
-
-#ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-#endif
-
-static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
-{
-	return syscall(__NR_open_tree, dfd, filename, flags);
 }
 
 static ssize_t write_nointr(int fd, const void *buf, size_t count)
···
 	ASSERT_EQ(mkdir("/mnt/D", 0777), 0);
 	img_fd = openat(-EBADF, "/mnt/C/ext4.img", O_CREAT | O_WRONLY, 0600);
 	ASSERT_GE(img_fd, 0);
-	ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0);
+	ASSERT_EQ(ftruncate(img_fd, 2147483648 /* 2 GB */), 0);
 	ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0);
 	ASSERT_EQ(system("mount -o loop -t ext4 /mnt/C/ext4.img /mnt/D/"), 0);
 	ASSERT_EQ(close(img_fd), 0);

tools/testing/selftests/pidfd/pidfd_bind_mount.c

···
 
 #include "pidfd.h"
 #include "../kselftest_harness.h"
-
-#ifndef __NR_open_tree
-	#if defined __alpha__
-		#define __NR_open_tree 538
-	#elif defined _MIPS_SIM
-		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
-			#define __NR_open_tree 4428
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
-			#define __NR_open_tree 6428
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
-			#define __NR_open_tree 5428
-		#endif
-	#elif defined __ia64__
-		#define __NR_open_tree (428 + 1024)
-	#else
-		#define __NR_open_tree 428
-	#endif
-#endif
-
-#ifndef __NR_move_mount
-	#if defined __alpha__
-		#define __NR_move_mount 539
-	#elif defined _MIPS_SIM
-		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
-			#define __NR_move_mount 4429
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
-			#define __NR_move_mount 6429
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
-			#define __NR_move_mount 5429
-		#endif
-	#elif defined __ia64__
-		#define __NR_move_mount (428 + 1024)
-	#else
-		#define __NR_move_mount 429
-	#endif
-#endif
-
-#ifndef MOVE_MOUNT_F_EMPTY_PATH
-#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
-#endif
-
-#ifndef MOVE_MOUNT_F_EMPTY_PATH
-#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
-#endif
-
-static inline int sys_move_mount(int from_dfd, const char *from_pathname,
-                                 int to_dfd, const char *to_pathname,
-                                 unsigned int flags)
-{
-        return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd,
-                       to_pathname, flags);
-}
-
-#ifndef OPEN_TREE_CLONE
-#define OPEN_TREE_CLONE 1
-#endif
-
-#ifndef OPEN_TREE_CLOEXEC
-#define OPEN_TREE_CLOEXEC O_CLOEXEC
-#endif
-
-#ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-#endif
-
-static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
-{
-	return syscall(__NR_open_tree, dfd, filename, flags);
-}
+#include "../filesystems/wrappers.h"
 
 FIXTURE(pidfd_bind_mount) {
 	char template[PATH_MAX];