fanotify: notify on mount attach and detach

Add notifications for attaching and detaching mounts. The following new
event masks are added:

FAN_MNT_ATTACH - Mount was attached
FAN_MNT_DETACH - Mount was detached

If a mount is moved, then the event is reported with (FAN_MNT_ATTACH |
FAN_MNT_DETACH).

These events add an info record of type FAN_EVENT_INFO_TYPE_MNT containing
these fields identifying the affected mounts:

__u64 mnt_id - the ID of the mount (see statmount(2))

FAN_REPORT_MNT must be supplied to fanotify_init() to receive these events
and no other type of event can be received with this report type.

Marks are added with FAN_MARK_MNTNS, which records the mount namespace from
an nsfs file (e.g. /proc/self/ns/mnt).

Signed-off-by: Miklos Szeredi <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Christian Brauner <[e-mail]>

fs/mount.h

···
 {
 	return container_of(ns, struct mnt_namespace, ns);
 }
+
+struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry);

fs/namespace.c

···
 	}
 }
 
+struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry)
+{
+	if (!is_mnt_ns_file(dentry))
+		return NULL;
+
+	return to_mnt_ns(get_proc_ns(dentry->d_inode));
+}
+
 static bool mnt_ns_loop(struct dentry *dentry)
 {
 	/* Could bind mounting the mount namespace inode cause a
 	 * mount namespace loop?
 	 */
-	struct mnt_namespace *mnt_ns;
-	if (!is_mnt_ns_file(dentry))
+	struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry);
+
+	if (!mnt_ns)
 		return false;
 
-	mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode));
 	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
 }
 

fs/notify/fanotify/fanotify.c

···
 	case FANOTIFY_EVENT_TYPE_FS_ERROR:
 		return fanotify_error_event_equal(FANOTIFY_EE(old),
 						  FANOTIFY_EE(new));
+	case FANOTIFY_EVENT_TYPE_MNT:
+		return false;
 	default:
 		WARN_ON_ONCE(1);
 	}
···
 	pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
 		 __func__, iter_info->report_mask, event_mask, data, data_type);
 
-	if (!fid_mode) {
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+		if (data_type != FSNOTIFY_EVENT_MNT)
+			return 0;
+	} else if (!fid_mode) {
 		/* Do we have path to open a file descriptor? */
 		if (!path)
 			return 0;
···
 	return &pevent->fae;
 }
 
+static struct fanotify_event *fanotify_alloc_mnt_event(u64 mnt_id, gfp_t gfp)
+{
+	struct fanotify_mnt_event *pevent;
+
+	pevent = kmem_cache_alloc(fanotify_mnt_event_cachep, gfp);
+	if (!pevent)
+		return NULL;
+
+	pevent->fae.type = FANOTIFY_EVENT_TYPE_MNT;
+	pevent->mnt_id = mnt_id;
+
+	return &pevent->fae;
+}
+
 static struct fanotify_event *fanotify_alloc_perm_event(const void *data,
 							int data_type,
 							gfp_t gfp)
···
 					      fid_mode);
 	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
+	u64 mnt_id = fsnotify_data_mnt_id(data, data_type);
 	struct mem_cgroup *old_memcg;
 	struct dentry *moved = NULL;
 	struct inode *child = NULL;
···
 						  moved, &hash, gfp);
 	} else if (fid_mode) {
 		event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
-	} else {
+	} else if (path) {
 		event = fanotify_alloc_path_event(path, &hash, gfp);
+	} else if (mnt_id) {
+		event = fanotify_alloc_mnt_event(mnt_id, gfp);
+	} else {
+		WARN_ON_ONCE(1);
 	}
 
 	if (!event)
···
 	BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
 	BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 24);
 
 	mask = fanotify_group_event_mask(group, iter_info, &match_mask,
 					 mask, data, data_type, dir);
···
 	mempool_free(fee, &group->fanotify_data.error_events_pool);
 }
 
+static void fanotify_free_mnt_event(struct fanotify_event *event)
+{
+	kmem_cache_free(fanotify_mnt_event_cachep, FANOTIFY_ME(event));
+}
+
 static void fanotify_free_event(struct fsnotify_group *group,
 				struct fsnotify_event *fsn_event)
 {
···
 		break;
 	case FANOTIFY_EVENT_TYPE_FS_ERROR:
 		fanotify_free_error_event(group, event);
+		break;
+	case FANOTIFY_EVENT_TYPE_MNT:
+		fanotify_free_mnt_event(event);
 		break;
 	default:
 		WARN_ON_ONCE(1);

fs/notify/fanotify/fanotify.h

···
 extern struct kmem_cache *fanotify_fid_event_cachep;
 extern struct kmem_cache *fanotify_path_event_cachep;
 extern struct kmem_cache *fanotify_perm_event_cachep;
+extern struct kmem_cache *fanotify_mnt_event_cachep;
 
 /* Possible states of the permission event */
 enum {
···
 	FANOTIFY_EVENT_TYPE_PATH_PERM,
 	FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
 	FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+	FANOTIFY_EVENT_TYPE_MNT,
 	__FANOTIFY_EVENT_TYPE_NUM
 };
 
···
 	struct path path;
 };
 
+struct fanotify_mnt_event {
+	struct fanotify_event fae;
+	u64 mnt_id;
+};
+
 static inline struct fanotify_path_event *
 FANOTIFY_PE(struct fanotify_event *event)
 {
 	return container_of(event, struct fanotify_path_event, fae);
+}
+
+static inline struct fanotify_mnt_event *
+FANOTIFY_ME(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_mnt_event, fae);
 }
 
 /*
···
 static inline bool fanotify_is_error_event(u32 mask)
 {
 	return mask & FAN_FS_ERROR;
+}
+
+static inline bool fanotify_is_mnt_event(u32 mask)
+{
+	return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH);
 }
 
 static inline const struct path *fanotify_event_path(struct fanotify_event *event)

fs/notify/fanotify/fanotify_user.c

···
 struct kmem_cache *fanotify_fid_event_cachep __ro_after_init;
 struct kmem_cache *fanotify_path_event_cachep __ro_after_init;
 struct kmem_cache *fanotify_perm_event_cachep __ro_after_init;
+struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init;
 
 #define FANOTIFY_EVENT_ALIGN 4
 #define FANOTIFY_FID_INFO_HDR_LEN \
···
 	(sizeof(struct fanotify_event_info_error))
 #define FANOTIFY_RANGE_INFO_LEN \
 	(sizeof(struct fanotify_event_info_range))
+#define FANOTIFY_MNT_INFO_LEN \
+	(sizeof(struct fanotify_event_info_mnt))
 
 static int fanotify_fid_info_len(int fh_len, int name_len)
 {
···
 		fh_len = fanotify_event_object_fh_len(event);
 		event_len += fanotify_fid_info_len(fh_len, dot_len);
 	}
+	if (fanotify_is_mnt_event(event->mask))
+		event_len += FANOTIFY_MNT_INFO_LEN;
 
 	if (info_mode & FAN_REPORT_PIDFD)
 		event_len += FANOTIFY_PIDFD_INFO_LEN;
···
 	spin_unlock(&group->notification_lock);
 
 	return -ENOENT;
+}
+
+static size_t copy_mnt_info_to_user(struct fanotify_event *event,
+				    char __user *buf, int count)
+{
+	struct fanotify_event_info_mnt info = { };
+
+	info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT;
+	info.hdr.len = FANOTIFY_MNT_INFO_LEN;
+
+	if (WARN_ON(count < info.hdr.len))
+		return -EFAULT;
+
+	info.mnt_id = FANOTIFY_ME(event)->mnt_id;
+
+	if (copy_to_user(buf, &info, sizeof(info)))
+		return -EFAULT;
+
+	return info.hdr.len;
 }
 
 static size_t copy_error_info_to_user(struct fanotify_event *event,
···
 
 	if (fanotify_event_has_access_range(event)) {
 		ret = copy_range_info_to_user(event, buf, count);
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
+	if (fanotify_is_mnt_event(event->mask)) {
+		ret = copy_mnt_info_to_user(event, buf, count);
 		if (ret < 0)
 			return ret;
 		buf += ret;
···
 	if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
 		return -EINVAL;
 
+	/* Don't allow mixing mnt events with inode events for now */
+	if (flags & FAN_REPORT_MNT) {
+		if (class != FAN_CLASS_NOTIF)
+			return -EINVAL;
+		if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR))
+			return -EINVAL;
+	}
+
 	if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
 		return -EINVAL;
 
···
 			    int dfd, const char  __user *pathname)
 {
 	struct inode *inode = NULL;
-	struct vfsmount *mnt = NULL;
 	struct fsnotify_group *group;
 	struct path path;
 	struct fan_fsid __fsid, *fsid = NULL;
···
 	unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
 	unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
 	unsigned int obj_type, fid_mode;
-	void *obj;
+	void *obj = NULL;
 	u32 umask = 0;
 	int ret;
 
···
 		break;
 	case FAN_MARK_FILESYSTEM:
 		obj_type = FSNOTIFY_OBJ_TYPE_SB;
+		break;
+	case FAN_MARK_MNTNS:
+		obj_type = FSNOTIFY_OBJ_TYPE_MNTNS;
 		break;
 	default:
 		return -EINVAL;
···
 		return -EINVAL;
 	group = fd_file(f)->private_data;
 
+	/* Only report mount events on mnt namespace */
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+		if (mask & ~FANOTIFY_MOUNT_EVENTS)
+			return -EINVAL;
+		if (mark_type != FAN_MARK_MNTNS)
+			return -EINVAL;
+	} else {
+		if (mask & FANOTIFY_MOUNT_EVENTS)
+			return -EINVAL;
+		if (mark_type == FAN_MARK_MNTNS)
+			return -EINVAL;
+	}
+
 	/*
 	 * An unprivileged user is not allowed to setup mount nor filesystem
 	 * marks.  This also includes setting up such marks by a group that
···
 	 * point.
 	 */
 	fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
-	if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
+	if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) &&
 	    (!fid_mode || mark_type == FAN_MARK_MOUNT))
 		return -EINVAL;
 
···
 	}
 
 	/* inode held in place by reference to path; group by fget on fd */
-	if (mark_type == FAN_MARK_INODE) {
+	if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) {
 		inode = path.dentry->d_inode;
 		obj = inode;
-	} else {
-		mnt = path.mnt;
-		if (mark_type == FAN_MARK_MOUNT)
-			obj = mnt;
-		else
-			obj = mnt->mnt_sb;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+		obj = path.mnt;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) {
+		obj = path.mnt->mnt_sb;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		obj = mnt_ns_from_dentry(path.dentry);
 	}
+
+	ret = -EINVAL;
+	if (!obj)
+		goto path_put_and_out;
 
 	/*
 	 * If some other task has this inode open for write we should not add
···
 	 */
 	if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) &&
 	    !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) {
-		ret = mnt ? -EINVAL : -EISDIR;
+		ret = !inode ? -EINVAL : -EISDIR;
 		/* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
 		if (ignore == FAN_MARK_IGNORE &&
-		    (mnt || S_ISDIR(inode->i_mode)))
+		    (!inode || S_ISDIR(inode->i_mode)))
 			goto path_put_and_out;
 
 		ret = 0;
···
 	}
 
 	/* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
-	if (mnt || !S_ISDIR(inode->i_mode)) {
+	if (!inode || !S_ISDIR(inode->i_mode)) {
 		mask &= ~FAN_EVENT_ON_CHILD;
 		umask = FAN_EVENT_ON_CHILD;
 		/*
···
 				     FANOTIFY_DEFAULT_MAX_USER_MARKS);
 
 	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 13);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
 
 	fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
···
 		fanotify_perm_event_cachep =
 			KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
 	}
+	fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC);
 
 	fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
 	init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =

fs/notify/fdinfo.c

···
 
 		seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
 			   sb->s_dev, mflags, mark->mask, mark->ignore_mask);
+	} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector);
+
+		seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask);
 	}
 }
 

include/linux/fanotify.h

···
 
 #define FANOTIFY_FID_BITS	(FAN_REPORT_DFID_NAME_TARGET)
 
-#define FANOTIFY_INFO_MODES	(FANOTIFY_FID_BITS | FAN_REPORT_PIDFD)
+#define FANOTIFY_INFO_MODES	(FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT)
 
 /*
  * fanotify_init() flags that require CAP_SYS_ADMIN.
···
 					 FAN_REPORT_PIDFD | \
 					 FAN_REPORT_FD_ERROR | \
 					 FAN_UNLIMITED_QUEUE | \
-					 FAN_UNLIMITED_MARKS)
+					 FAN_UNLIMITED_MARKS | \
+					 FAN_REPORT_MNT)
 
 /*
  * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN.
···
 #define FANOTIFY_INTERNAL_GROUP_FLAGS	(FANOTIFY_UNPRIV)
 
 #define FANOTIFY_MARK_TYPE_BITS	(FAN_MARK_INODE | FAN_MARK_MOUNT | \
-				 FAN_MARK_FILESYSTEM)
+				 FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS)
 
 #define FANOTIFY_MARK_CMD_BITS	(FAN_MARK_ADD | FAN_MARK_REMOVE | \
 				 FAN_MARK_FLUSH)
···
 /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */
 #define FANOTIFY_ERROR_EVENTS	(FAN_FS_ERROR)
 
+#define FANOTIFY_MOUNT_EVENTS	(FAN_MNT_ATTACH | FAN_MNT_DETACH)
+
 /* Events that user can request to be notified on */
 #define FANOTIFY_EVENTS		(FANOTIFY_PATH_EVENTS | \
 				 FANOTIFY_INODE_EVENTS | \
-				 FANOTIFY_ERROR_EVENTS)
+				 FANOTIFY_ERROR_EVENTS | \
+				 FANOTIFY_MOUNT_EVENTS)
 
 /* Extra flags that may be reported with event or control handling of events */
 #define FANOTIFY_EVENT_FLAGS	(FAN_EVENT_ON_CHILD | FAN_ONDIR)

include/uapi/linux/fanotify.h

···
 /* #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_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)
···
 #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
···
 #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
···
 	__u32 pad;
 	__u64 offset;
 	__u64 count;
+};
+
+struct fanotify_event_info_mnt {
+	struct fanotify_event_info_header hdr;
+	__u64 mnt_id;
 };
 
 /*